Dealing with the Unknown: Pessimistic Offline Reinforcement Learning.
Jinning LiChen TangMasayoshi TomizukaWei ZhanPublished in: CoRL (2021)
Keyphrases
- reinforcement learning
- function approximation
- markov decision processes
- real world
- machine learning
- reinforcement learning algorithms
- state space
- multi agent
- model free
- artificial intelligence
- databases
- real time
- relational reinforcement learning
- stochastic approximation
- temporal difference learning
- control problems
- policy search
- database
- evaluation function
- optimal policy
- dynamic programming
- active learning
- multi agent systems
- case study
- information systems