Towards Minimax Optimality of Model-based Robust Reinforcement Learning.
Pierre ClavierErwan Le PennecMatthieu GeistPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- model free
- function approximation
- average reward reinforcement learning
- computationally efficient
- machine learning
- multi agent
- real time
- reinforcement learning algorithms
- learning process
- state space
- upper bound
- optimal policy
- transfer learning
- image sequences
- optimal control
- robust estimation
- computer vision
- imperfect information