Multiagent learning using a variable learning rate

DOI10.1016/S0004-3702(02)00121-2zbMath0995.68075MaRDI QIDQ1605410

Michael Bowling, Manuela M. Veloso

Publication date: 15 July 2002

Published in: Artificial Intelligence (Search for Journal in Brave)

zbMATH Keywords

game theory; reinforcement learning; multiagent learning

Mathematics Subject Classification ID

68T05: Learning and adaptive systems in artificial intelligence

Related Items

SOLVING CONSTRAINED OPTIMIZATION PROBLEMS USING PROBABILITY COLLECTIVES AND A PENALTY FUNCTION APPROACH, On-policy concurrent reinforcement learning, A Probability Collectives Approach for Multi-Agent Distributed and Cooperative Optimization with Tolerance for Agent Failure, GENERAL PROOF OF CONVERGENCE OF THE NASH-Q-LEARNING ALGORITHM, Unnamed Item, FUZZY STATE AGGREGATION AND POLICY HILL CLIMBING FOR STOCHASTIC ENVIRONMENTS, $Q$-Learning in a Stochastic Stackelberg Game between an Uninformed Leader and a Naive Follower, Belief and truth in hypothesised behaviours, Learning to compete, coordinate, and cooperate in repeated games using reinforcement learning, Learning efficient Nash equilibria in distributed systems, Learning with policy prediction in continuous state-action multi-agent decision processes, Perspectives on multiagent learning, An adjustment scheme for nonlinear pricing problem with two buyers, EAQR: a multiagent Q-learning algorithm for coordination of multiple agents, Autonomous agents modelling other agents: a comprehensive survey and open problems, Decentralized reinforcement learning of robot behaviors, Continuous learning methods in two-buyer pricing problem, Negotiating team formation using deep reinforcement learning, Single-leader-multiple-follower games with boundedly rational agents, A distributed algorithm to obtain repeated games equilibria with discounting, When autonomous agents model other agents: an appeal for altered judgment coupled with mouths, ears, and a little more tape, Analysis of Hannan consistent selection for Monte Carlo tree search in simultaneous move games, AWESOME: a general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponents, A general criterion and an algorithmic framework for learning in multi-agent systems, Introduction to the special issue on learning and computational game theory, Exploration-exploitation in multi-agent learning: catastrophe theory meets game theory, COOPERATIVE LEARNING BY POLICY-SHARING IN MULTIPLE AGENTS, Sharing in teams of heterogeneous, collaborative learning agents

Cites Work

• On-line learning and the metrical task system problem
• Convergence results for single-step on-policy reinforcement-learning algorithms
• Two-person nonzero-sum games and quadratic programming
• An iterative method of solving a game
• Equilibrium points in n -person games
• Stochastic Games
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item