Old Web
English
Sign In
Acemap
>
Paper
>
Offline Constrained Multi-Objective Reinforcement Learning via Pessimistic Dual Value Iteration
Offline Constrained Multi-Objective Reinforcement Learning via Pessimistic Dual Value Iteration
2021
Runzhe Wu
Yufeng Zhang
Zhuoran Yang
Zhaoran Wang
Keywords:
Pessimism
DUAL (cognitive architecture)
Mathematical optimization
Reinforcement learning
Markov decision process
Computer science
Correction
Source
Cite
Save
Machine Reading By IdeaReader
0
References
0
Citations
NaN
KQI
[]