Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity.
Kaiqing ZhangSham M. KakadeTamer BasarLin F. YangPublished in: J. Mach. Learn. Res. (2023)
Keyphrases
- markov games
- sample complexity
- multiagent reinforcement learning
- multi agent
- reinforcement learning
- reinforcement learning algorithms
- markov decision processes
- model free
- learning problems
- learning algorithm
- markov decision process
- theoretical analysis
- stochastic games
- supervised learning
- multiagent systems
- control problems
- state space
- upper bound
- lower bound
- cooperative
- active learning
- training examples
- generalization error
- special case
- sample size
- temporal difference
- optimal policy
- policy iteration
- machine learning
- finite state
- function approximation
- multi agent systems
- autonomous agents
- multiple agents
- infinite horizon
- training set
- partially observable markov decision processes
- initial state
- learning automata
- cross validation
- dynamic programming