Towards Minimax Optimal Reinforcement Learning in Factored Markov Decision Processes
–Neural Information Processing Systems
We study minimax optimal reinforcement learning in episodic factored Markov decision processes (FMDPs), which are MDPs with conditionally independent transition components.
Neural Information Processing Systems
Aug-17-2025, 01:18:58 GMT
- Country:
- North America
- Canada (0.04)
- United States > Massachusetts
- Middlesex County > Cambridge (0.14)
- Europe > United Kingdom
- England > Cambridgeshire > Cambridge (0.04)
- Asia > Middle East
- Jordan (0.04)
- North America