Nearly Minimax Optimal Reinforcement Learning with Linear Function Approximation.
Pihe HuYu ChenLongbo HuangPublished in: CoRR (2022)
Keyphrases
- function approximation
- reinforcement learning
- function approximators
- temporal difference learning algorithms
- temporal difference learning
- temporal difference
- mountain car
- model free
- state action space
- dynamic programming
- learning tasks
- tile coding
- optimal control
- radial basis function
- td learning
- support vector
- machine learning
- reinforcement learning algorithms
- average reward
- control policy
- state space
- markov decision processes
- markov decision problems
- continuous state
- policy evaluation
- pattern recognition
- collaborative filtering
- optimal policy
- e learning