Towards Hyperparameter-free Policy Selection for Offline Reinforcement Learning.
Siyuan ZhangNan JiangPublished in: NeurIPS (2021)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- markov decision process
- action selection
- state and action spaces
- function approximation
- action space
- reward function
- markov decision problems
- state space
- partially observable environments
- policy gradient
- model selection
- model free
- real time
- reinforcement learning algorithms
- partially observable
- approximate dynamic programming
- actor critic
- state action
- partially observable domains
- temporal difference
- control policy
- gaussian processes
- selection algorithm
- transfer learning
- learning algorithm
- gaussian process
- markov decision processes
- continuous state spaces
- dynamic programming
- reinforcement learning problems
- multi agent
- machine learning