English
Related papers

Related papers: The State-Action-Reward-State-Action Algorithm in …

200 papers

In this work, we develop a reinforcement learning protocol for a multiagent coordination task in a discrete state and action space: an iterated prisoner's dilemma game extended into a team based, winner-take all tournament, which forces the…

Computer Science and Game Theory · Computer Science 2018-06-18 Aaron Goodman

Purpose: We propose a model to present a possible mechanism for obtaining sizeable behavioural structures by simulating an agent based on the evolutionary public good game with available social learning. Methods: The model considered a…

Computer Science and Game Theory · Computer Science 2019-10-29 Chulwook Park

Recent empirical studies suggest that heavy-tailed distributions of human activities are universal in real social dynamics [Muchnik, \emph{et al.}, Sci. Rep. \textbf{3}, 1783 (2013)]. On the other hand, community structure is ubiquitous in…

Physics and Society · Physics 2015-01-14 Zhi-Xi Wu , Zhihai Rong , Han-Xin Yang

The monotonous nature of repetitive cognitive training may cause losing interest in it and dropping out by older adults. This study introduces an adaptive technique that enables a Socially Assistive Robot (SAR) to select the most…

Robotics · Computer Science 2023-05-03 Eleonora Zedda , Marco Manca , Fabio Paterno , Carmen Santoro

Spatial evolutionary games provide a valuable framework for elucidating the emergence and maintenance of cooperative behavior. However, most previous studies assume that individuals are profiteers and neglect to consider the effects of…

Computer Science and Game Theory · Computer Science 2025-11-25 Bin Pi , Minyu Feng , Liang-Jian Deng

In many social dilemmas, individuals tend to generate a situation with low payoffs instead of a system optimum ("tragedy of the commons"). Is the routing of traffic a similar problem? In order to address this question, we present…

Physics and Society · Physics 2007-05-23 Dirk Helbing , Martin Schonhof , Hans-Ulrich Stark , Janusz A. Holyst

In this paper, we study how the pro-social impact due to the vigilance by other individuals is conditioned by both environmental and evolutionary effects. To this aim, we consider a known model where agents play a Prisoner's Dilemma Game…

Physics and Society · Physics 2017-01-16 María Pereda , Daniele Vilone

In human societies the probability of strategy adoption from a given person may be affected by the personal features. Now we investigate how an artificially imposed restricted ability to reproduce, overruling ones fitness, affects an…

Populations and Evolution · Quantitative Biology 2008-04-10 A. Szolnoki , M. Perc , G. Szabo

Punishment, especially selfish punishment, has recently been identified as a potent promoter in sustaining or even enhancing the cooperation among unrelated individuals. However, without other key mechanisms, the first-order social dilemma…

Physics and Society · Physics 2014-08-13 Pengbi Cui , Zhi-Xi Wu

Partner selection is an important process in many social interactions, permitting individuals to decrease the risks associated with cooperation. In large populations, defectors may escape punishment by roving from partner to partner, but…

adap-org · Physics 2008-02-03 Dan Ashlock , Mark D. Smucker , E. Ann Stanley , Leigh Tesfatsion

The evolutionary persistence of symbiotic associations is a puzzle. Adaptation should eliminate cooperative traits if it is possible to enjoy the advantages of cooperation without reciprocating - a facet of cooperation known in game theory…

Populations and Evolution · Quantitative Biology 2009-11-10 Marcus R. Frean , Edward R. Abraham

We considered a three-strategy game with the characteristics of the prisoner's dilemma and stag hunt games. This game was inspired by recent experimental studies that elucidated the role of individual solutions. People who adopt individual…

Populations and Evolution · Quantitative Biology 2025-02-11 Hirofumi Takesue

We consider the multi-agent reinforcement learning setting with imperfect information in which each agent is trying to maximize its own utility. The reward function depends on the hidden state (or goal) of both agents, so the agents must…

Artificial Intelligence · Computer Science 2018-03-28 Roberta Raileanu , Emily Denton , Arthur Szlam , Rob Fergus

Reinforcement learning methods require careful design involving a reward function to obtain the desired action policy for a given task. In the absence of hand-crafted reward functions, prior work on the topic has proposed several methods…

Machine Learning · Computer Science 2018-10-16 Daiki Kimura , Subhajit Chaudhury , Ryuki Tachibana , Sakyasingha Dasgupta

In multiagent environments, the capability of learning is important for an agent to behave appropriately in face of unknown opponents and dynamic environment. From the system designer's perspective, it is desirable if the agents can learn…

Artificial Intelligence · Computer Science 2018-03-09 Chengwei Zhang , Xiaohong Li , Jianye Hao , Siqi Chen , Karl Tuyls , Wanli Xue

Ecology and evolution are inherently linked, and studying a mathematical model that considers both holds promise of insightful discoveries related to the dynamics of cooperation. In the present article, we use the prisoner's dilemma (PD)…

Populations and Evolution · Quantitative Biology 2021-08-10 Sayantan Nag Chowdhury , Srilena Kundu , Jeet Banerjee , Matjaž Perc , Dibakar Ghosh

There is a recent trend of applying multi-agent reinforcement learning (MARL) to train an agent that can cooperate with humans in a zero-shot fashion without using any human data. The typical workflow is to first repeatedly run self-play…

Artificial Intelligence · Computer Science 2023-02-06 Chao Yu , Jiaxuan Gao , Weilin Liu , Botian Xu , Hao Tang , Jiaqi Yang , Yu Wang , Yi Wu

Individual rationality, which involves maximizing expected individual returns, does not always lead to high-utility individual or group outcomes in multi-agent problems. For instance, in multi-agent social dilemmas, Reinforcement Learning…

Evolutionary game dynamics in finite populations provides a new framework to understand the selection of traits with frequency-dependent fitness. Recently, a simple but fundamental law of evolutionary dynamics, which we call {\sigma} law,…

Populations and Evolution · Quantitative Biology 2012-04-19 Changbing Tang , Xiang Li , Lang Cao , Jingyuan Zhan

Reinforcement Learning (RL) is known to be often unsuccessful in environments with sparse extrinsic rewards. A possible countermeasure is to endow RL agents with an intrinsic reward function, or 'intrinsic motivation', which rewards the…

Artificial Intelligence · Computer Science 2021-07-16 Francesco Massari , Martin Biehl , Lisa Meeden , Ryota Kanai