Distance-Sensitive Offline Reinforcement Learning.
Jianxiong LiXianyuan ZhanHaoran XuXiangyu ZhuJingjing LiuYa-Qin ZhangPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- function approximation
- real time
- distance function
- distance measure
- euclidean distance
- state space
- model free
- optimal control
- distance transform
- dynamic programming
- learning process
- artificial neural networks
- multi agent
- genetic algorithm
- transition model
- optimal policy
- distance matrix
- distance measurement
- learning agents
- monte carlo
- decision making
- information retrieval