reinforcement learning Search Results


reinforcement learning models  (MathWorks Inc)
94
MathWorks Inc reinforcement learning models
Fig. 1. Rationale, design, and analytic approach. Individuals learn from experience by selecting an action, observing its outcome, and updating the expected reward value of future actions. Value updates are made using PEs, which reflect the discrepancy between expected and obtained outcomes such that better- than-expected outcomes lead to positive PEs and worse-than-expected outcomes lead to negative PEs. Other salient social information can also be integrated with experience to influence social decision-making, as when the reputation of one’s partner predicts decisions to trust them even when reputation is unrelated to the partner’s actual behavior (27, 41). (A) Consider the decision about whether to buy a friend a holiday gift. Reputational information (e.g., news of a friend’s immoral behavior; blue circle) can be integrated with <t>reinforcement</t> history (e.g., did the friend buy you a gift last year? green circle) to affect one’s policy toward their social counterpart. Critically, decisions that correctly anticipate the behavior of one’s social partner (correctly predicting they bought you a gift, or correctly predicting they did not buy you a gift) yield positive PEs according to our policy model, leading to a cycle of reciprocity even when no actual reward is received. (B) Participants played a modified iterative social trust game with three fictional trustees, in which they had the option to keep an initial endowment or invest it in the hopes of increasing their profit if the trustee also invested. Pretask vignettes were used to manipulate trustees’ reputations (blue box). To manipulate reinforcement history, trustees returned at varying rates across rich, poor, and neutral blocks (green box). On trials where participants kept, counterfactual feedback about what the trustee would have chosen was provided, even though it did not affect the trial payout. (C) The policy model posits that individuals learn from social feedback to optimize their approach, or policy, toward their social counterpart, leading to better anticipation of the counterpart’s behavior. One implication of this is that correct predictions of the trustee’s behavior will lead to positive reward PEs, even if no actual reward is provided. This can be seen by comparing the expected direction of PEs in a model in which participants track actual rewards (column 3) vs. a model in which they track the success of their policy toward the counterpart (column 4). We propose that policy PEs are primarily encoded within the brain’s default network. Image credit: Default network figure adapted from ref. 35. (D) MSEM was used to evaluate whether between-person variables (e.g., policy PEs encoded in the default network) moderate the effect of design variables on trial-level decision-making. Personality traits were introduced as between-person predictors of policy PEs in the default network. Formal tests of mediation were then used to examine the indirect effect of traits on behavior via learning signals (highlighted lines).
Reinforcement Learning Models, supplied by MathWorks Inc, used in various techniques. Bioz Stars score: 94/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/reinforcement learning models/product/MathWorks Inc
Average 94 stars, based on 1 article reviews
reinforcement learning models - by Bioz Stars, 2026-03
94/100 stars
  Buy from Supplier
multi-agent reinforcement learning  (Innov X Systems)
90
Innov X Systems multi-agent reinforcement learning
Fig. 1. Rationale, design, and analytic approach. Individuals learn from experience by selecting an action, observing its outcome, and updating the expected reward value of future actions. Value updates are made using PEs, which reflect the discrepancy between expected and obtained outcomes such that better- than-expected outcomes lead to positive PEs and worse-than-expected outcomes lead to negative PEs. Other salient social information can also be integrated with experience to influence social decision-making, as when the reputation of one’s partner predicts decisions to trust them even when reputation is unrelated to the partner’s actual behavior (27, 41). (A) Consider the decision about whether to buy a friend a holiday gift. Reputational information (e.g., news of a friend’s immoral behavior; blue circle) can be integrated with <t>reinforcement</t> history (e.g., did the friend buy you a gift last year? green circle) to affect one’s policy toward their social counterpart. Critically, decisions that correctly anticipate the behavior of one’s social partner (correctly predicting they bought you a gift, or correctly predicting they did not buy you a gift) yield positive PEs according to our policy model, leading to a cycle of reciprocity even when no actual reward is received. (B) Participants played a modified iterative social trust game with three fictional trustees, in which they had the option to keep an initial endowment or invest it in the hopes of increasing their profit if the trustee also invested. Pretask vignettes were used to manipulate trustees’ reputations (blue box). To manipulate reinforcement history, trustees returned at varying rates across rich, poor, and neutral blocks (green box). On trials where participants kept, counterfactual feedback about what the trustee would have chosen was provided, even though it did not affect the trial payout. (C) The policy model posits that individuals learn from social feedback to optimize their approach, or policy, toward their social counterpart, leading to better anticipation of the counterpart’s behavior. One implication of this is that correct predictions of the trustee’s behavior will lead to positive reward PEs, even if no actual reward is provided. This can be seen by comparing the expected direction of PEs in a model in which participants track actual rewards (column 3) vs. a model in which they track the success of their policy toward the counterpart (column 4). We propose that policy PEs are primarily encoded within the brain’s default network. Image credit: Default network figure adapted from ref. 35. (D) MSEM was used to evaluate whether between-person variables (e.g., policy PEs encoded in the default network) moderate the effect of design variables on trial-level decision-making. Personality traits were introduced as between-person predictors of policy PEs in the default network. Formal tests of mediation were then used to examine the indirect effect of traits on behavior via learning signals (highlighted lines).
Multi Agent Reinforcement Learning, supplied by Innov X Systems, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/multi-agent reinforcement learning/product/Innov X Systems
Average 90 stars, based on 1 article reviews
multi-agent reinforcement learning - by Bioz Stars, 2026-03
90/100 stars
  Buy from Supplier
deep reinforcement learning  (Deepmind Technologies Ltd)
90
Deepmind Technologies Ltd deep reinforcement learning
Fig. 1. Rationale, design, and analytic approach. Individuals learn from experience by selecting an action, observing its outcome, and updating the expected reward value of future actions. Value updates are made using PEs, which reflect the discrepancy between expected and obtained outcomes such that better- than-expected outcomes lead to positive PEs and worse-than-expected outcomes lead to negative PEs. Other salient social information can also be integrated with experience to influence social decision-making, as when the reputation of one’s partner predicts decisions to trust them even when reputation is unrelated to the partner’s actual behavior (27, 41). (A) Consider the decision about whether to buy a friend a holiday gift. Reputational information (e.g., news of a friend’s immoral behavior; blue circle) can be integrated with <t>reinforcement</t> history (e.g., did the friend buy you a gift last year? green circle) to affect one’s policy toward their social counterpart. Critically, decisions that correctly anticipate the behavior of one’s social partner (correctly predicting they bought you a gift, or correctly predicting they did not buy you a gift) yield positive PEs according to our policy model, leading to a cycle of reciprocity even when no actual reward is received. (B) Participants played a modified iterative social trust game with three fictional trustees, in which they had the option to keep an initial endowment or invest it in the hopes of increasing their profit if the trustee also invested. Pretask vignettes were used to manipulate trustees’ reputations (blue box). To manipulate reinforcement history, trustees returned at varying rates across rich, poor, and neutral blocks (green box). On trials where participants kept, counterfactual feedback about what the trustee would have chosen was provided, even though it did not affect the trial payout. (C) The policy model posits that individuals learn from social feedback to optimize their approach, or policy, toward their social counterpart, leading to better anticipation of the counterpart’s behavior. One implication of this is that correct predictions of the trustee’s behavior will lead to positive reward PEs, even if no actual reward is provided. This can be seen by comparing the expected direction of PEs in a model in which participants track actual rewards (column 3) vs. a model in which they track the success of their policy toward the counterpart (column 4). We propose that policy PEs are primarily encoded within the brain’s default network. Image credit: Default network figure adapted from ref. 35. (D) MSEM was used to evaluate whether between-person variables (e.g., policy PEs encoded in the default network) moderate the effect of design variables on trial-level decision-making. Personality traits were introduced as between-person predictors of policy PEs in the default network. Formal tests of mediation were then used to examine the indirect effect of traits on behavior via learning signals (highlighted lines).
Deep Reinforcement Learning, supplied by Deepmind Technologies Ltd, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/deep reinforcement learning/product/Deepmind Technologies Ltd
Average 90 stars, based on 1 article reviews
deep reinforcement learning - by Bioz Stars, 2026-03
90/100 stars
  Buy from Supplier
deep reinforcement learning  (Kuang Lung Shing)
90
Kuang Lung Shing deep reinforcement learning
Fig. 1. Rationale, design, and analytic approach. Individuals learn from experience by selecting an action, observing its outcome, and updating the expected reward value of future actions. Value updates are made using PEs, which reflect the discrepancy between expected and obtained outcomes such that better- than-expected outcomes lead to positive PEs and worse-than-expected outcomes lead to negative PEs. Other salient social information can also be integrated with experience to influence social decision-making, as when the reputation of one’s partner predicts decisions to trust them even when reputation is unrelated to the partner’s actual behavior (27, 41). (A) Consider the decision about whether to buy a friend a holiday gift. Reputational information (e.g., news of a friend’s immoral behavior; blue circle) can be integrated with <t>reinforcement</t> history (e.g., did the friend buy you a gift last year? green circle) to affect one’s policy toward their social counterpart. Critically, decisions that correctly anticipate the behavior of one’s social partner (correctly predicting they bought you a gift, or correctly predicting they did not buy you a gift) yield positive PEs according to our policy model, leading to a cycle of reciprocity even when no actual reward is received. (B) Participants played a modified iterative social trust game with three fictional trustees, in which they had the option to keep an initial endowment or invest it in the hopes of increasing their profit if the trustee also invested. Pretask vignettes were used to manipulate trustees’ reputations (blue box). To manipulate reinforcement history, trustees returned at varying rates across rich, poor, and neutral blocks (green box). On trials where participants kept, counterfactual feedback about what the trustee would have chosen was provided, even though it did not affect the trial payout. (C) The policy model posits that individuals learn from social feedback to optimize their approach, or policy, toward their social counterpart, leading to better anticipation of the counterpart’s behavior. One implication of this is that correct predictions of the trustee’s behavior will lead to positive reward PEs, even if no actual reward is provided. This can be seen by comparing the expected direction of PEs in a model in which participants track actual rewards (column 3) vs. a model in which they track the success of their policy toward the counterpart (column 4). We propose that policy PEs are primarily encoded within the brain’s default network. Image credit: Default network figure adapted from ref. 35. (D) MSEM was used to evaluate whether between-person variables (e.g., policy PEs encoded in the default network) moderate the effect of design variables on trial-level decision-making. Personality traits were introduced as between-person predictors of policy PEs in the default network. Formal tests of mediation were then used to examine the indirect effect of traits on behavior via learning signals (highlighted lines).
Deep Reinforcement Learning, supplied by Kuang Lung Shing, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/deep reinforcement learning/product/Kuang Lung Shing
Average 90 stars, based on 1 article reviews
deep reinforcement learning - by Bioz Stars, 2026-03
90/100 stars
  Buy from Supplier
an introduction to deep reinforcement learning  (LAVET Pharmaceuticals Ltd)
90
LAVET Pharmaceuticals Ltd an introduction to deep reinforcement learning
Fig. 1. Rationale, design, and analytic approach. Individuals learn from experience by selecting an action, observing its outcome, and updating the expected reward value of future actions. Value updates are made using PEs, which reflect the discrepancy between expected and obtained outcomes such that better- than-expected outcomes lead to positive PEs and worse-than-expected outcomes lead to negative PEs. Other salient social information can also be integrated with experience to influence social decision-making, as when the reputation of one’s partner predicts decisions to trust them even when reputation is unrelated to the partner’s actual behavior (27, 41). (A) Consider the decision about whether to buy a friend a holiday gift. Reputational information (e.g., news of a friend’s immoral behavior; blue circle) can be integrated with <t>reinforcement</t> history (e.g., did the friend buy you a gift last year? green circle) to affect one’s policy toward their social counterpart. Critically, decisions that correctly anticipate the behavior of one’s social partner (correctly predicting they bought you a gift, or correctly predicting they did not buy you a gift) yield positive PEs according to our policy model, leading to a cycle of reciprocity even when no actual reward is received. (B) Participants played a modified iterative social trust game with three fictional trustees, in which they had the option to keep an initial endowment or invest it in the hopes of increasing their profit if the trustee also invested. Pretask vignettes were used to manipulate trustees’ reputations (blue box). To manipulate reinforcement history, trustees returned at varying rates across rich, poor, and neutral blocks (green box). On trials where participants kept, counterfactual feedback about what the trustee would have chosen was provided, even though it did not affect the trial payout. (C) The policy model posits that individuals learn from social feedback to optimize their approach, or policy, toward their social counterpart, leading to better anticipation of the counterpart’s behavior. One implication of this is that correct predictions of the trustee’s behavior will lead to positive reward PEs, even if no actual reward is provided. This can be seen by comparing the expected direction of PEs in a model in which participants track actual rewards (column 3) vs. a model in which they track the success of their policy toward the counterpart (column 4). We propose that policy PEs are primarily encoded within the brain’s default network. Image credit: Default network figure adapted from ref. 35. (D) MSEM was used to evaluate whether between-person variables (e.g., policy PEs encoded in the default network) moderate the effect of design variables on trial-level decision-making. Personality traits were introduced as between-person predictors of policy PEs in the default network. Formal tests of mediation were then used to examine the indirect effect of traits on behavior via learning signals (highlighted lines).
An Introduction To Deep Reinforcement Learning, supplied by LAVET Pharmaceuticals Ltd, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/an introduction to deep reinforcement learning/product/LAVET Pharmaceuticals Ltd
Average 90 stars, based on 1 article reviews
an introduction to deep reinforcement learning - by Bioz Stars, 2026-03
90/100 stars
  Buy from Supplier
reinforcement learning based mac protocol uw-aloha-q  (IEEE Access)
90
IEEE Access reinforcement learning based mac protocol uw-aloha-q
Fig. 1. Rationale, design, and analytic approach. Individuals learn from experience by selecting an action, observing its outcome, and updating the expected reward value of future actions. Value updates are made using PEs, which reflect the discrepancy between expected and obtained outcomes such that better- than-expected outcomes lead to positive PEs and worse-than-expected outcomes lead to negative PEs. Other salient social information can also be integrated with experience to influence social decision-making, as when the reputation of one’s partner predicts decisions to trust them even when reputation is unrelated to the partner’s actual behavior (27, 41). (A) Consider the decision about whether to buy a friend a holiday gift. Reputational information (e.g., news of a friend’s immoral behavior; blue circle) can be integrated with <t>reinforcement</t> history (e.g., did the friend buy you a gift last year? green circle) to affect one’s policy toward their social counterpart. Critically, decisions that correctly anticipate the behavior of one’s social partner (correctly predicting they bought you a gift, or correctly predicting they did not buy you a gift) yield positive PEs according to our policy model, leading to a cycle of reciprocity even when no actual reward is received. (B) Participants played a modified iterative social trust game with three fictional trustees, in which they had the option to keep an initial endowment or invest it in the hopes of increasing their profit if the trustee also invested. Pretask vignettes were used to manipulate trustees’ reputations (blue box). To manipulate reinforcement history, trustees returned at varying rates across rich, poor, and neutral blocks (green box). On trials where participants kept, counterfactual feedback about what the trustee would have chosen was provided, even though it did not affect the trial payout. (C) The policy model posits that individuals learn from social feedback to optimize their approach, or policy, toward their social counterpart, leading to better anticipation of the counterpart’s behavior. One implication of this is that correct predictions of the trustee’s behavior will lead to positive reward PEs, even if no actual reward is provided. This can be seen by comparing the expected direction of PEs in a model in which participants track actual rewards (column 3) vs. a model in which they track the success of their policy toward the counterpart (column 4). We propose that policy PEs are primarily encoded within the brain’s default network. Image credit: Default network figure adapted from ref. 35. (D) MSEM was used to evaluate whether between-person variables (e.g., policy PEs encoded in the default network) moderate the effect of design variables on trial-level decision-making. Personality traits were introduced as between-person predictors of policy PEs in the default network. Formal tests of mediation were then used to examine the indirect effect of traits on behavior via learning signals (highlighted lines).
Reinforcement Learning Based Mac Protocol Uw Aloha Q, supplied by IEEE Access, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/reinforcement learning based mac protocol uw-aloha-q/product/IEEE Access
Average 90 stars, based on 1 article reviews
reinforcement learning based mac protocol uw-aloha-q - by Bioz Stars, 2026-03
90/100 stars
  Buy from Supplier
generative tensorial reinforcement learning (gentrl)  (Insilico Medicine)
90
Insilico Medicine generative tensorial reinforcement learning (gentrl)
Fig. 1. Rationale, design, and analytic approach. Individuals learn from experience by selecting an action, observing its outcome, and updating the expected reward value of future actions. Value updates are made using PEs, which reflect the discrepancy between expected and obtained outcomes such that better- than-expected outcomes lead to positive PEs and worse-than-expected outcomes lead to negative PEs. Other salient social information can also be integrated with experience to influence social decision-making, as when the reputation of one’s partner predicts decisions to trust them even when reputation is unrelated to the partner’s actual behavior (27, 41). (A) Consider the decision about whether to buy a friend a holiday gift. Reputational information (e.g., news of a friend’s immoral behavior; blue circle) can be integrated with <t>reinforcement</t> history (e.g., did the friend buy you a gift last year? green circle) to affect one’s policy toward their social counterpart. Critically, decisions that correctly anticipate the behavior of one’s social partner (correctly predicting they bought you a gift, or correctly predicting they did not buy you a gift) yield positive PEs according to our policy model, leading to a cycle of reciprocity even when no actual reward is received. (B) Participants played a modified iterative social trust game with three fictional trustees, in which they had the option to keep an initial endowment or invest it in the hopes of increasing their profit if the trustee also invested. Pretask vignettes were used to manipulate trustees’ reputations (blue box). To manipulate reinforcement history, trustees returned at varying rates across rich, poor, and neutral blocks (green box). On trials where participants kept, counterfactual feedback about what the trustee would have chosen was provided, even though it did not affect the trial payout. (C) The policy model posits that individuals learn from social feedback to optimize their approach, or policy, toward their social counterpart, leading to better anticipation of the counterpart’s behavior. One implication of this is that correct predictions of the trustee’s behavior will lead to positive reward PEs, even if no actual reward is provided. This can be seen by comparing the expected direction of PEs in a model in which participants track actual rewards (column 3) vs. a model in which they track the success of their policy toward the counterpart (column 4). We propose that policy PEs are primarily encoded within the brain’s default network. Image credit: Default network figure adapted from ref. 35. (D) MSEM was used to evaluate whether between-person variables (e.g., policy PEs encoded in the default network) moderate the effect of design variables on trial-level decision-making. Personality traits were introduced as between-person predictors of policy PEs in the default network. Formal tests of mediation were then used to examine the indirect effect of traits on behavior via learning signals (highlighted lines).
Generative Tensorial Reinforcement Learning (Gentrl), supplied by Insilico Medicine, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/generative tensorial reinforcement learning (gentrl)/product/Insilico Medicine
Average 90 stars, based on 1 article reviews
generative tensorial reinforcement learning (gentrl) - by Bioz Stars, 2026-03
90/100 stars
  Buy from Supplier
data-efficient reinforcement learning with self-predictive representations  (Schwarzer GmbH)
90
Schwarzer GmbH data-efficient reinforcement learning with self-predictive representations
Fig. 1. Rationale, design, and analytic approach. Individuals learn from experience by selecting an action, observing its outcome, and updating the expected reward value of future actions. Value updates are made using PEs, which reflect the discrepancy between expected and obtained outcomes such that better- than-expected outcomes lead to positive PEs and worse-than-expected outcomes lead to negative PEs. Other salient social information can also be integrated with experience to influence social decision-making, as when the reputation of one’s partner predicts decisions to trust them even when reputation is unrelated to the partner’s actual behavior (27, 41). (A) Consider the decision about whether to buy a friend a holiday gift. Reputational information (e.g., news of a friend’s immoral behavior; blue circle) can be integrated with <t>reinforcement</t> history (e.g., did the friend buy you a gift last year? green circle) to affect one’s policy toward their social counterpart. Critically, decisions that correctly anticipate the behavior of one’s social partner (correctly predicting they bought you a gift, or correctly predicting they did not buy you a gift) yield positive PEs according to our policy model, leading to a cycle of reciprocity even when no actual reward is received. (B) Participants played a modified iterative social trust game with three fictional trustees, in which they had the option to keep an initial endowment or invest it in the hopes of increasing their profit if the trustee also invested. Pretask vignettes were used to manipulate trustees’ reputations (blue box). To manipulate reinforcement history, trustees returned at varying rates across rich, poor, and neutral blocks (green box). On trials where participants kept, counterfactual feedback about what the trustee would have chosen was provided, even though it did not affect the trial payout. (C) The policy model posits that individuals learn from social feedback to optimize their approach, or policy, toward their social counterpart, leading to better anticipation of the counterpart’s behavior. One implication of this is that correct predictions of the trustee’s behavior will lead to positive reward PEs, even if no actual reward is provided. This can be seen by comparing the expected direction of PEs in a model in which participants track actual rewards (column 3) vs. a model in which they track the success of their policy toward the counterpart (column 4). We propose that policy PEs are primarily encoded within the brain’s default network. Image credit: Default network figure adapted from ref. 35. (D) MSEM was used to evaluate whether between-person variables (e.g., policy PEs encoded in the default network) moderate the effect of design variables on trial-level decision-making. Personality traits were introduced as between-person predictors of policy PEs in the default network. Formal tests of mediation were then used to examine the indirect effect of traits on behavior via learning signals (highlighted lines).
Data Efficient Reinforcement Learning With Self Predictive Representations, supplied by Schwarzer GmbH, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/data-efficient reinforcement learning with self-predictive representations/product/Schwarzer GmbH
Average 90 stars, based on 1 article reviews
data-efficient reinforcement learning with self-predictive representations - by Bioz Stars, 2026-03
90/100 stars
  Buy from Supplier
markov games as a framework for multi-agent reinforcement learning  (New Brunswick Scientific)
90
New Brunswick Scientific markov games as a framework for multi-agent reinforcement learning
Fig. 1. Rationale, design, and analytic approach. Individuals learn from experience by selecting an action, observing its outcome, and updating the expected reward value of future actions. Value updates are made using PEs, which reflect the discrepancy between expected and obtained outcomes such that better- than-expected outcomes lead to positive PEs and worse-than-expected outcomes lead to negative PEs. Other salient social information can also be integrated with experience to influence social decision-making, as when the reputation of one’s partner predicts decisions to trust them even when reputation is unrelated to the partner’s actual behavior (27, 41). (A) Consider the decision about whether to buy a friend a holiday gift. Reputational information (e.g., news of a friend’s immoral behavior; blue circle) can be integrated with <t>reinforcement</t> history (e.g., did the friend buy you a gift last year? green circle) to affect one’s policy toward their social counterpart. Critically, decisions that correctly anticipate the behavior of one’s social partner (correctly predicting they bought you a gift, or correctly predicting they did not buy you a gift) yield positive PEs according to our policy model, leading to a cycle of reciprocity even when no actual reward is received. (B) Participants played a modified iterative social trust game with three fictional trustees, in which they had the option to keep an initial endowment or invest it in the hopes of increasing their profit if the trustee also invested. Pretask vignettes were used to manipulate trustees’ reputations (blue box). To manipulate reinforcement history, trustees returned at varying rates across rich, poor, and neutral blocks (green box). On trials where participants kept, counterfactual feedback about what the trustee would have chosen was provided, even though it did not affect the trial payout. (C) The policy model posits that individuals learn from social feedback to optimize their approach, or policy, toward their social counterpart, leading to better anticipation of the counterpart’s behavior. One implication of this is that correct predictions of the trustee’s behavior will lead to positive reward PEs, even if no actual reward is provided. This can be seen by comparing the expected direction of PEs in a model in which participants track actual rewards (column 3) vs. a model in which they track the success of their policy toward the counterpart (column 4). We propose that policy PEs are primarily encoded within the brain’s default network. Image credit: Default network figure adapted from ref. 35. (D) MSEM was used to evaluate whether between-person variables (e.g., policy PEs encoded in the default network) moderate the effect of design variables on trial-level decision-making. Personality traits were introduced as between-person predictors of policy PEs in the default network. Formal tests of mediation were then used to examine the indirect effect of traits on behavior via learning signals (highlighted lines).
Markov Games As A Framework For Multi Agent Reinforcement Learning, supplied by New Brunswick Scientific, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/markov games as a framework for multi-agent reinforcement learning/product/New Brunswick Scientific
Average 90 stars, based on 1 article reviews
markov games as a framework for multi-agent reinforcement learning - by Bioz Stars, 2026-03
90/100 stars
  Buy from Supplier
gan and reinforcement learning (rl) systems  (Insilico Medicine)
90
Insilico Medicine gan and reinforcement learning (rl) systems
Fig. 1. Rationale, design, and analytic approach. Individuals learn from experience by selecting an action, observing its outcome, and updating the expected reward value of future actions. Value updates are made using PEs, which reflect the discrepancy between expected and obtained outcomes such that better- than-expected outcomes lead to positive PEs and worse-than-expected outcomes lead to negative PEs. Other salient social information can also be integrated with experience to influence social decision-making, as when the reputation of one’s partner predicts decisions to trust them even when reputation is unrelated to the partner’s actual behavior (27, 41). (A) Consider the decision about whether to buy a friend a holiday gift. Reputational information (e.g., news of a friend’s immoral behavior; blue circle) can be integrated with <t>reinforcement</t> history (e.g., did the friend buy you a gift last year? green circle) to affect one’s policy toward their social counterpart. Critically, decisions that correctly anticipate the behavior of one’s social partner (correctly predicting they bought you a gift, or correctly predicting they did not buy you a gift) yield positive PEs according to our policy model, leading to a cycle of reciprocity even when no actual reward is received. (B) Participants played a modified iterative social trust game with three fictional trustees, in which they had the option to keep an initial endowment or invest it in the hopes of increasing their profit if the trustee also invested. Pretask vignettes were used to manipulate trustees’ reputations (blue box). To manipulate reinforcement history, trustees returned at varying rates across rich, poor, and neutral blocks (green box). On trials where participants kept, counterfactual feedback about what the trustee would have chosen was provided, even though it did not affect the trial payout. (C) The policy model posits that individuals learn from social feedback to optimize their approach, or policy, toward their social counterpart, leading to better anticipation of the counterpart’s behavior. One implication of this is that correct predictions of the trustee’s behavior will lead to positive reward PEs, even if no actual reward is provided. This can be seen by comparing the expected direction of PEs in a model in which participants track actual rewards (column 3) vs. a model in which they track the success of their policy toward the counterpart (column 4). We propose that policy PEs are primarily encoded within the brain’s default network. Image credit: Default network figure adapted from ref. 35. (D) MSEM was used to evaluate whether between-person variables (e.g., policy PEs encoded in the default network) moderate the effect of design variables on trial-level decision-making. Personality traits were introduced as between-person predictors of policy PEs in the default network. Formal tests of mediation were then used to examine the indirect effect of traits on behavior via learning signals (highlighted lines).
Gan And Reinforcement Learning (Rl) Systems, supplied by Insilico Medicine, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/gan and reinforcement learning (rl) systems/product/Insilico Medicine
Average 90 stars, based on 1 article reviews
gan and reinforcement learning (rl) systems - by Bioz Stars, 2026-03
90/100 stars
  Buy from Supplier
adaptive modular reinforcement learning algorithm  (IEEE Access)
90
IEEE Access adaptive modular reinforcement learning algorithm
Fig. 1. Rationale, design, and analytic approach. Individuals learn from experience by selecting an action, observing its outcome, and updating the expected reward value of future actions. Value updates are made using PEs, which reflect the discrepancy between expected and obtained outcomes such that better- than-expected outcomes lead to positive PEs and worse-than-expected outcomes lead to negative PEs. Other salient social information can also be integrated with experience to influence social decision-making, as when the reputation of one’s partner predicts decisions to trust them even when reputation is unrelated to the partner’s actual behavior (27, 41). (A) Consider the decision about whether to buy a friend a holiday gift. Reputational information (e.g., news of a friend’s immoral behavior; blue circle) can be integrated with <t>reinforcement</t> history (e.g., did the friend buy you a gift last year? green circle) to affect one’s policy toward their social counterpart. Critically, decisions that correctly anticipate the behavior of one’s social partner (correctly predicting they bought you a gift, or correctly predicting they did not buy you a gift) yield positive PEs according to our policy model, leading to a cycle of reciprocity even when no actual reward is received. (B) Participants played a modified iterative social trust game with three fictional trustees, in which they had the option to keep an initial endowment or invest it in the hopes of increasing their profit if the trustee also invested. Pretask vignettes were used to manipulate trustees’ reputations (blue box). To manipulate reinforcement history, trustees returned at varying rates across rich, poor, and neutral blocks (green box). On trials where participants kept, counterfactual feedback about what the trustee would have chosen was provided, even though it did not affect the trial payout. (C) The policy model posits that individuals learn from social feedback to optimize their approach, or policy, toward their social counterpart, leading to better anticipation of the counterpart’s behavior. One implication of this is that correct predictions of the trustee’s behavior will lead to positive reward PEs, even if no actual reward is provided. This can be seen by comparing the expected direction of PEs in a model in which participants track actual rewards (column 3) vs. a model in which they track the success of their policy toward the counterpart (column 4). We propose that policy PEs are primarily encoded within the brain’s default network. Image credit: Default network figure adapted from ref. 35. (D) MSEM was used to evaluate whether between-person variables (e.g., policy PEs encoded in the default network) moderate the effect of design variables on trial-level decision-making. Personality traits were introduced as between-person predictors of policy PEs in the default network. Formal tests of mediation were then used to examine the indirect effect of traits on behavior via learning signals (highlighted lines).
Adaptive Modular Reinforcement Learning Algorithm, supplied by IEEE Access, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/adaptive modular reinforcement learning algorithm/product/IEEE Access
Average 90 stars, based on 1 article reviews
adaptive modular reinforcement learning algorithm - by Bioz Stars, 2026-03
90/100 stars
  Buy from Supplier
cooperative multi-agent reinforcement learning  (Curran Associates Inc)
90
Curran Associates Inc cooperative multi-agent reinforcement learning
Fig. 1. Rationale, design, and analytic approach. Individuals learn from experience by selecting an action, observing its outcome, and updating the expected reward value of future actions. Value updates are made using PEs, which reflect the discrepancy between expected and obtained outcomes such that better- than-expected outcomes lead to positive PEs and worse-than-expected outcomes lead to negative PEs. Other salient social information can also be integrated with experience to influence social decision-making, as when the reputation of one’s partner predicts decisions to trust them even when reputation is unrelated to the partner’s actual behavior (27, 41). (A) Consider the decision about whether to buy a friend a holiday gift. Reputational information (e.g., news of a friend’s immoral behavior; blue circle) can be integrated with <t>reinforcement</t> history (e.g., did the friend buy you a gift last year? green circle) to affect one’s policy toward their social counterpart. Critically, decisions that correctly anticipate the behavior of one’s social partner (correctly predicting they bought you a gift, or correctly predicting they did not buy you a gift) yield positive PEs according to our policy model, leading to a cycle of reciprocity even when no actual reward is received. (B) Participants played a modified iterative social trust game with three fictional trustees, in which they had the option to keep an initial endowment or invest it in the hopes of increasing their profit if the trustee also invested. Pretask vignettes were used to manipulate trustees’ reputations (blue box). To manipulate reinforcement history, trustees returned at varying rates across rich, poor, and neutral blocks (green box). On trials where participants kept, counterfactual feedback about what the trustee would have chosen was provided, even though it did not affect the trial payout. (C) The policy model posits that individuals learn from social feedback to optimize their approach, or policy, toward their social counterpart, leading to better anticipation of the counterpart’s behavior. One implication of this is that correct predictions of the trustee’s behavior will lead to positive reward PEs, even if no actual reward is provided. This can be seen by comparing the expected direction of PEs in a model in which participants track actual rewards (column 3) vs. a model in which they track the success of their policy toward the counterpart (column 4). We propose that policy PEs are primarily encoded within the brain’s default network. Image credit: Default network figure adapted from ref. 35. (D) MSEM was used to evaluate whether between-person variables (e.g., policy PEs encoded in the default network) moderate the effect of design variables on trial-level decision-making. Personality traits were introduced as between-person predictors of policy PEs in the default network. Formal tests of mediation were then used to examine the indirect effect of traits on behavior via learning signals (highlighted lines).
Cooperative Multi Agent Reinforcement Learning, supplied by Curran Associates Inc, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/cooperative multi-agent reinforcement learning/product/Curran Associates Inc
Average 90 stars, based on 1 article reviews
cooperative multi-agent reinforcement learning - by Bioz Stars, 2026-03
90/100 stars
  Buy from Supplier

Image Search Results


Fig. 1. Rationale, design, and analytic approach. Individuals learn from experience by selecting an action, observing its outcome, and updating the expected reward value of future actions. Value updates are made using PEs, which reflect the discrepancy between expected and obtained outcomes such that better- than-expected outcomes lead to positive PEs and worse-than-expected outcomes lead to negative PEs. Other salient social information can also be integrated with experience to influence social decision-making, as when the reputation of one’s partner predicts decisions to trust them even when reputation is unrelated to the partner’s actual behavior (27, 41). (A) Consider the decision about whether to buy a friend a holiday gift. Reputational information (e.g., news of a friend’s immoral behavior; blue circle) can be integrated with reinforcement history (e.g., did the friend buy you a gift last year? green circle) to affect one’s policy toward their social counterpart. Critically, decisions that correctly anticipate the behavior of one’s social partner (correctly predicting they bought you a gift, or correctly predicting they did not buy you a gift) yield positive PEs according to our policy model, leading to a cycle of reciprocity even when no actual reward is received. (B) Participants played a modified iterative social trust game with three fictional trustees, in which they had the option to keep an initial endowment or invest it in the hopes of increasing their profit if the trustee also invested. Pretask vignettes were used to manipulate trustees’ reputations (blue box). To manipulate reinforcement history, trustees returned at varying rates across rich, poor, and neutral blocks (green box). On trials where participants kept, counterfactual feedback about what the trustee would have chosen was provided, even though it did not affect the trial payout. (C) The policy model posits that individuals learn from social feedback to optimize their approach, or policy, toward their social counterpart, leading to better anticipation of the counterpart’s behavior. One implication of this is that correct predictions of the trustee’s behavior will lead to positive reward PEs, even if no actual reward is provided. This can be seen by comparing the expected direction of PEs in a model in which participants track actual rewards (column 3) vs. a model in which they track the success of their policy toward the counterpart (column 4). We propose that policy PEs are primarily encoded within the brain’s default network. Image credit: Default network figure adapted from ref. 35. (D) MSEM was used to evaluate whether between-person variables (e.g., policy PEs encoded in the default network) moderate the effect of design variables on trial-level decision-making. Personality traits were introduced as between-person predictors of policy PEs in the default network. Formal tests of mediation were then used to examine the indirect effect of traits on behavior via learning signals (highlighted lines).

Journal: Proceedings of the National Academy of Sciences of the United States of America

Article Title: Callousness, exploitativeness, and tracking of cooperation incentives in the human default network.

doi: 10.1073/pnas.2307221121

Figure Lengend Snippet: Fig. 1. Rationale, design, and analytic approach. Individuals learn from experience by selecting an action, observing its outcome, and updating the expected reward value of future actions. Value updates are made using PEs, which reflect the discrepancy between expected and obtained outcomes such that better- than-expected outcomes lead to positive PEs and worse-than-expected outcomes lead to negative PEs. Other salient social information can also be integrated with experience to influence social decision-making, as when the reputation of one’s partner predicts decisions to trust them even when reputation is unrelated to the partner’s actual behavior (27, 41). (A) Consider the decision about whether to buy a friend a holiday gift. Reputational information (e.g., news of a friend’s immoral behavior; blue circle) can be integrated with reinforcement history (e.g., did the friend buy you a gift last year? green circle) to affect one’s policy toward their social counterpart. Critically, decisions that correctly anticipate the behavior of one’s social partner (correctly predicting they bought you a gift, or correctly predicting they did not buy you a gift) yield positive PEs according to our policy model, leading to a cycle of reciprocity even when no actual reward is received. (B) Participants played a modified iterative social trust game with three fictional trustees, in which they had the option to keep an initial endowment or invest it in the hopes of increasing their profit if the trustee also invested. Pretask vignettes were used to manipulate trustees’ reputations (blue box). To manipulate reinforcement history, trustees returned at varying rates across rich, poor, and neutral blocks (green box). On trials where participants kept, counterfactual feedback about what the trustee would have chosen was provided, even though it did not affect the trial payout. (C) The policy model posits that individuals learn from social feedback to optimize their approach, or policy, toward their social counterpart, leading to better anticipation of the counterpart’s behavior. One implication of this is that correct predictions of the trustee’s behavior will lead to positive reward PEs, even if no actual reward is provided. This can be seen by comparing the expected direction of PEs in a model in which participants track actual rewards (column 3) vs. a model in which they track the success of their policy toward the counterpart (column 4). We propose that policy PEs are primarily encoded within the brain’s default network. Image credit: Default network figure adapted from ref. 35. (D) MSEM was used to evaluate whether between-person variables (e.g., policy PEs encoded in the default network) moderate the effect of design variables on trial-level decision-making. Personality traits were introduced as between-person predictors of policy PEs in the default network. Formal tests of mediation were then used to examine the indirect effect of traits on behavior via learning signals (highlighted lines).

Article Snippet: Reinforcement learning models were fit using the variational Bayesian analysis toolbox in MATLAB, which leverages parameter estimates from the full sample to constrain individual parameter estimates, reducing the risk of misestimation in poorly performing participants (64).

Techniques: Modification