A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games.
Samuel SokotaRyan D'OrazioJ. Zico KolterNicolas LoizouMarc LanctotIoannis MitliagkasNoam BrownChristian KroerPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- game theoretic
- imperfect information
- reinforcement learning algorithms
- nash equilibria
- perfect information
- nash equilibrium
- optimal strategy
- game theory
- learning agents
- repeated games
- markov decision processes
- function approximation
- pure strategy
- multiagent learning
- model free
- decision problems
- fixed point
- multi agent
- long run
- robotic control
- temporal difference learning
- reinforcement learning methods
- machine learning
- temporal difference
- incomplete information
- state space
- single agent
- stochastic games
- optimal policy
- multi agent reinforcement learning
- opponent modeling
- dynamic programming
- optimal control
- dynamical systems
- transfer learning
- resource allocation
- solution concepts
- supervised learning
- learning algorithm