Multi-objective reinforcement learning
From HandWiki
Multi-objective reinforcement learning (MORL) is a form of reinforcement learning concerned with conflicting alternatives. It is distinct from multi-objective optimization in that it is concerned with agents acting in environments.[1][2]
References
- ↑ "A practical guide to multi-objective reinforcement learning and planning". Autonomous Agents and Multi-Agent Systems 36. 2022. doi:10.1007/s10458-022-09552-y.,
- ↑ Tzeng, Gwo-Hshiung; Huang, Jih-Jeng (2011). Multiple Attribute Decision Making: Methods and Applications (1st ed.). ISBN 9781439861578.
 |  |
