Provably Efficient Neural Offline Reinforcement Learning via Perturbed Rewards.
Thanh Nguyen-TangRaman AroraPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- state space
- temporal difference
- markov decision processes
- neural network
- learning algorithm
- dynamic programming
- model free
- real time
- data sets
- database
- function approximation
- fitted q iteration
- state and action spaces
- computationally expensive
- cost effective
- optimal policy
- computationally efficient
- supervised learning