Refined Regret for Adversarial MDPs with Linear Function Approximation.
Yan DaiHaipeng LuoChen-Yu WeiJulian ZimmertPublished in: CoRR (2023)
Keyphrases
- function approximation
- reinforcement learning
- temporal difference learning algorithms
- function approximators
- markov decision processes
- reinforcement learning problems
- temporal difference
- policy evaluation
- reward function
- temporal difference learning
- markov decision problems
- multi agent
- model free
- learning tasks
- state space
- radial basis function
- reinforcement learning algorithms
- policy iteration
- policy search
- machine learning
- policy gradient
- markov decision process
- sufficient conditions
- linear programming