Model-Free Robust Reinforcement Learning with Sample Complexity Analysis.
Yudan WangShaofeng ZouYue WangPublished in: CoRR (2024)
Keyphrases
- model free
- complexity analysis
- reinforcement learning
- reinforcement learning algorithms
- function approximation
- temporal difference
- rl algorithms
- theoretical analysis
- policy iteration
- learning algorithm
- neural network
- lower bound
- state space
- reinforcement learning methods
- average reward
- temporal difference learning
- multi agent
- machine learning
- policy evaluation
- learning tasks
- sample size
- supervised learning
- expert systems
- computational complexity