Efficient Incremental Offline Reinforcement Learning With Sparse Broad Critic Approximation.
Liang YaoBaoliang ZhaoXin XuZiwen WangPak-Kin WongYing HuPublished in: IEEE Trans. Syst. Man Cybern. Syst. (2024)
Keyphrases
- efficient incremental
- reinforcement learning
- actor critic
- temporal difference
- function approximation
- reinforcement learning algorithms
- policy gradient
- sparse approximation
- materialized views
- state space
- approximate dynamic programming
- function approximators
- model free
- machine learning
- approximation algorithms
- markov decision processes
- real time
- high dimensional
- optimal control
- approximation methods
- optimal policy
- monte carlo
- management system