Model-based Offline Reinforcement Learning with Local Misspecification.
Kefan DongYannis Flet-BerliacAllen NieEmma BrunskillPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- model free
- function approximation
- state space
- reinforcement learning algorithms
- real time
- machine learning
- temporal difference
- data driven
- markov decision processes
- learning process
- dynamic programming
- transfer learning
- learning problems
- artificial neural networks
- search algorithm
- database systems
- learning algorithm
- robot control
- action space
- reinforcement learning methods