Settling the Sample Complexity of Model-Based Offline Reinforcement Learning.
Gen LiLaixi ShiYuxin ChenYuejie ChiYuting WeiPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- model free
- function approximation
- data driven
- learning algorithm
- state space
- data sets
- relational reinforcement learning
- control problems
- markov decision processes
- dynamic programming
- real time
- supervised learning
- optimal policy
- search algorithm
- case study
- learning classifier systems
- neural network
- temporal difference
- databases
- learning agents