When Is Generalizable Reinforcement Learning Tractable?
Dhruv MalikYuanzhi LiPradeep RavikumarPublished in: NeurIPS (2021)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- learning algorithm
- optimal policy
- state space
- temporal difference
- computational complexity
- robotic control
- multi agent
- learning process
- relational reinforcement learning
- np complete
- genetic algorithm
- markov decision processes
- temporal difference learning
- neural network
- model free
- real time
- exact computation
- transition model
- version spaces
- computational problems
- markov decision process
- real world
- machine learning
- search engine
- dynamic programming
- np hard
- active learning
- bayesian networks