On the Role of General Function Approximation in Offline Reinforcement Learning.
Chenjie MaoQiaosheng ZhangZhen WangXuelong LiPublished in: ICLR (2024)
Keyphrases
- function approximation
- reinforcement learning
- temporal difference learning
- temporal difference learning algorithms
- temporal difference
- state action space
- radial basis function
- mountain car
- tile coding
- function approximators
- model free
- learning tasks
- multi agent
- optimal policy
- machine learning
- reinforcement learning algorithms
- state space
- optimal control
- genetic algorithm
- linear combination
- td learning
- collaborative filtering
- text mining
- graph cuts
- markov decision processes