Performance Bounds for Policy-Based Reinforcement Learning Methods in Zero-Sum Markov Games with Linear Function Approximation.
Anna WinnickiR. SrikantPublished in: CDC (2023)
Keyphrases
- markov games
- reinforcement learning algorithms
- function approximation
- reinforcement learning methods
- reinforcement learning
- reinforcement learning problems
- function approximators
- model free
- temporal difference
- temporal difference learning
- markov decision processes
- stochastic games
- natural actor critic
- markov decision process
- control problems
- state space
- policy gradient
- multiagent reinforcement learning
- optimal policy
- radial basis function
- learning tasks
- reward function
- markov decision problems
- machine learning
- active learning
- learning algorithm
- genetic algorithm