Near-Optimal Deployment Efficiency in Reward-Free Reinforcement Learning with Linear Function Approximation.
Dan QiaoYu-Xiang WangPublished in: ICLR (2023)
Keyphrases
- function approximation
- reinforcement learning
- temporal difference learning algorithms
- function approximators
- temporal difference
- state space
- temporal difference learning
- model free
- reinforcement learning algorithms
- state action space
- multi agent
- mountain car
- markov decision processes
- machine learning
- policy gradient
- reward function
- optimal control
- optimal policy
- learning algorithm
- dynamic programming
- learning tasks
- transfer learning
- radial basis function
- supervised learning
- partially observable
- learning agent
- knn
- reinforcement learning methods
- markov decision problems
- continuous state
- learning process
- policy evaluation
- feature space
- temporal difference methods
- decision trees