DOMAIN: MilDly COnservative Model-BAsed OfflINe Reinforcement Learning.
Xiao-Yin LiuXiao-Hu ZhouXiao-Liang XieShi-Qi LiuZhen-Qiu FengHao LiMei-Jiang GuiTian-Yu XiangDe-Xing HuangZeng-Guang HouPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- real time
- model free
- state space
- cross domain
- machine learning
- genetic algorithm
- reinforcement learning methods
- domain specific
- partially observable domains
- database
- temporal difference learning
- complex domains
- markov decision processes
- case based reasoning
- training data
- information retrieval