Coordination in multiagent reinforcement learning: a Bayesian approach

By Georgios Chalkiadakis, Craig Boutilier. 2003

186 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Management Science and Operations Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Management Science and Operations Research

Citations in the corpus

Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments (2017, background): “The importance of such modeling has been recognized by both reinforcement learning [3, 5] and cognitive science communities [10].”
Evolutionary Dynamics of Multi-Agent Learning: A Survey (2015, background): “Of particular interest to the discussion of multi-agent learning is the work of Chalkiadakis and Boutilier (2003), who use the Bayesian framework to explicitly model an agent's uncertainty about both the model of the environment and the strategies of the other agents.”
Nash Q-Learning for General-Sum Stochastic Games (2003, background): “Chalkiadakis and Boutilier (2003) proposed using Bayesian beliefs about other agents's strategies to guide the calculation.”
Autonomous agents modelling other agents: A comprehensive survey and open problems (2017, background): “discrete full Chalkiadakis and Boutilier [72] yes no yes yes no simult.”
Influence-Based Multi-Agent Exploration (2019, background): “Another Bayesian exploration approach has been proposed for learning in stateless repeated games (Chalkiadakis & Boutilier, 2003).”
Analyzing and visualizing multiagent rewards in dynamic and stochastic domains (2008, background): “Creating high-performance reward structures that promote coordination is a critical step in designing successful multiagent learning algorithms [8,15,18,21,22,26,31].”
Utile Coordination: Learning Interdependencies Among Cooperative Agents (2005, unknown): “[Chalkiadakis and Boutilier, 2003] Chalkiadakis, G. and Boutilier, C. (2003).”
Reasoning about Hypothetical Agent Behaviours and their Parameters (2017, methodology): “Moreover, our methods can deal with any parameterisation, while the methods proposed in [15,36] are specific to parameters of the used distributions (e.”
Nash Q-Learning for General-Sum Stochastic Games (2003, background): “Chalkiadakis and Boutilier (2003) proposed using Bayesian beliefs about other agents's strategies to guide the calculation.”
An Overview of Cooperative and Competitive Multiagent Learning (2005, background): “For example, agents may use Bayesian learning to create models of other agents, and use such models to anticipate their behavior [32].”
Cooperative Multi-Agent Learning: The State of the Art (2005, background): “Such an approach is used by Boutilier [22] and Chalkiadakis and Boutilier [47], who employ a Bayesian learning method for updating models of other agents.”
Collaborative Multiagent Reinforcement Learning by Payoff Propagation (2006, methodology): “Note that in our work we only consider temporal-difference methods; other multiagent reinforcementlearning methods exist that are based, for example, on policy search (Peshkin et al., 2000; Moallemi and Van Roy, 2004) or Bayesian approaches (Chalkiadakis and Boutilier, 2003).”