Reinforcement Learning in Factored MDPs: Oracle-Efficient Algorithms and Tighter Regret Bounds for the Non-Episodic Setting

Aug-16-2025, 14:51:44 GMT–Neural Information Processing Systems

We study reinforcement learning in non-episodic factored Markov decision processes (FMDPs).

algorithm, fmdp, mdp, (13 more...)

Neural Information Processing Systems

Aug-16-2025, 14:51:44 GMT

Conferences PDF

Country:
- Asia > Japan
  - Honshū > Chūbu > Ishikawa Prefecture > Kanazawa (0.04)
- North America
  - Canada (0.04)
  - United States > Michigan (0.04)

Technology:
- Information Technology > Artificial Intelligence > Machine Learning
  - Learning Graphical Models
    - Directed Networks > Bayesian Learning (0.47)
    - Undirected Networks > Markov Models (0.35)
  - Reinforcement Learning (1.00)