Reward-Free Model-Based Reinforcement Learning with Linear Function Approximation.
Weitong ZhangDongruo ZhouQuanquan GuPublished in: NeurIPS (2021)
Keyphrases
- function approximation
- reinforcement learning
- model based reinforcement learning
- temporal difference learning algorithms
- markov decision processes
- function approximators
- temporal difference
- state space
- model free
- policy gradient
- reinforcement learning algorithms
- markov decision problems
- reward function
- learning process
- radial basis function
- neural network
- machine learning
- partially observable markov decision processes
- learning tasks
- supervised learning
- dynamic programming
- multi agent