Options
Interactive Inverse Reinforcement Learning for Cooperative Games
Auteur(s)
Date de parution
2022
In
Proceedings of Machine Learning Research
Vol.
162
De la page
2393
A la page
2413
Résumé
We study the problem of designing autonomous agents that can learn to cooperate effectively with a potentially suboptimal partner while having no access to the joint reward function. This problem is modeled as a cooperative episodic two-agent Markov decision process. We assume control over only the first of the two agents in a Stackelberg formulation of the game, where the second agent is acting so as to maximise expected utility given the first agent’s policy. How should the first agent act in order to learn the joint reward function as quickly as possible and so that the joint policy is as close to optimal as possible? We analyse how knowledge about the reward function can be gained in this interactive two-agent scenario. We show that when the learning agent’s policies have a significant effect on the transition function, the reward function can be learned efficiently.
Notes
Proceedings of the 39th International Conference on Machine Learning
Identifiants
Autre version
https://proceedings.mlr.press/v162/buning22a.html
Type de publication
conference paper
Dossier(s) à télécharger
