Offline Reinforcement Learning with Additional Covering Distributions.
Chenjie MaoPublished in: Trans. Mach. Learn. Res. (2023)
Keyphrases
- reinforcement learning
- markov decision processes
- real time
- function approximation
- probability distribution
- random variables
- information retrieval
- decision trees
- dynamic programming
- model free
- gaussian distribution
- statistical distributions
- heavy tailed
- joint distribution
- optimal control
- transfer learning
- optimal policy
- state space
- objective function
- data sets