When Is Generalizable Reinforcement Learning Tractable?
Dhruv MalikYuanzhi LiPradeep RavikumarPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- function approximation
- computational complexity
- control problems
- learning algorithm
- action selection
- model free
- optimal policy
- state space
- np complete
- markov decision processes
- np hard
- optimal control
- temporal difference
- exact computation
- multi agent
- robotic control
- learning process
- partially observable
- machine learning
- multi agent reinforcement learning
- direct policy search