Multi-objective reinforcement learning

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

^ Hayes C, Radulescu R, Bargiacchi E, et al. (2022). "A practical guide to multi-objective reinforcement learning and planning". Autonomous Agents and Multi-Agent Systems. 36. arXiv:2103.09568. doi:10.1007/s10458-022-09552-y. S2CID 254235920.,
^ Tzeng, Gwo-Hshiung; Huang, Jih-Jeng (2011). Multiple Attribute Decision Making: Methods and Applications (1st ed.). ISBN 9781439861578.

This artificial intelligence-related article is a stub. You can help Wikipedia by expanding it.

[1] Hayes C, Radulescu R, Bargiacchi E, et al. (2022). "A practical guide to multi-objective reinforcement learning and planning". Autonomous Agents and Multi-Agent Systems. 36. arXiv:2103.09568. doi:10.1007/s10458-022-09552-y. S2CID 254235920.,

[2] Tzeng, Gwo-Hshiung; Huang, Jih-Jeng (2011). Multiple Attribute Decision Making: Methods and Applications (1st ed.). ISBN 9781439861578.

[1]

[2]