Nearly Horizon-Free Offline Reinforcement Learning.
Tongzheng RenJialian LiBo DaiSimon S. DuSujay SanghaviPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- real time
- function approximation
- state space
- multi agent
- machine learning
- learning algorithm
- optimal policy
- policy search
- model free
- reinforcement learning algorithms
- markov decision processes
- reinforcement learning methods
- control problems
- robotic control
- temporal difference
- learning problems
- markov chain
- supervised learning
- least squares
- dynamic programming
- control system
- active learning
- learning process
- case study
- search engine
- artificial intelligence
- information retrieval
- real world