Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations.
Yongyuan LiangYanchao SunRuijie ZhengXiangyu LiuTuomas SandholmFurong HuangStephen McAleerPublished in: CoRR (2023)
Keyphrases
- game theoretic
- reinforcement learning
- game theory
- decision problems
- nash equilibrium
- imperfect information
- state space
- pure nash equilibrium
- agent programming
- multiagent learning
- rational agents
- function approximation
- temporal information
- markov decision processes
- optimal policy
- agent behavior
- solution concepts
- dynamic programming
- multi agent
- decision making