The Generalization Gap in Offline Reinforcement Learning.
Ishita MedirattaQingfei YouMinqi JiangRoberta RaileanuPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- real time
- function approximation
- reinforcement learning algorithms
- markov decision processes
- state space
- learning algorithm
- multiscale
- optimal policy
- transition model
- temporal difference
- model free
- learning machines
- transfer learning
- database
- markov chain
- learning problems
- supervised learning
- optimal control
- least squares
- dynamic programming
- action selection
- feature selection
- search engine
- machine learning
- relational reinforcement learning