Reward-Free Model-Based Reinforcement Learning with Linear Function Approximation.
Weitong ZhangDongruo ZhouQuanquan GuPublished in: CoRR (2021)
Keyphrases
- function approximation
- reinforcement learning
- model based reinforcement learning
- temporal difference learning algorithms
- markov decision processes
- function approximators
- temporal difference
- model free
- machine learning
- policy gradient
- dynamic programming
- learning tasks
- learning algorithm
- markov decision problems
- optimal policy
- multi agent
- optimal control
- transfer learning
- state space
- radial basis function
- reinforcement learning algorithms
- learning experience