Hello, I have a model which has rewards for two different objectives, I want to know if there is a way to train a policy in rllib that could achieve a trade-off between these two objectives (finding pareto front maybe)? Is there any multi-objective rl algorithm implementation in the rllib? If not,…

How can I train a multi-objective model in rllib?

mannyv November 17, 2021, 1:42pm 4

Have a look at this related post.

Topic		Replies	Views
Multi-objective RL RLlib	6	1015	November 11, 2021
Multi reward optimization RLlib	6	413	September 29, 2021
Rewards leaks to different multi agent policies in training only Configure Algorithm, Training, Evaluation, Scaling	3	169	May 31, 2024
How to separate rewards between agent in adversarial multi agent env RLlib	3	484	August 16, 2022
How to add an extra model to a built-in Policy / Trainer? RLlib	1	287	June 27, 2022