Uncertainty-aware Distributional Offline Reinforcement Learning.
Xiaocong ChenSiyu WangTong YuLina YaoPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- partial observability
- function approximation
- real time
- inherent uncertainty
- uncertain data
- sequential decision problems
- temporal difference
- decision theory
- optimal policy
- learning algorithm
- markov decision processes
- co occurrence
- multi agent
- case study
- temporal difference learning
- multi agent reinforcement learning
- conditional probabilities
- model free
- optimal control
- decision problems
- information systems
- data mining