Truly Batch Model-Free Inverse Reinforcement Learning about Multiple Intentions

Giorgia Ramponi, Amarildo Likmeta, Alberto Maria Metelli, Andrea Tirinzoni, Marcello Restelli
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, PMLR 108:2359-2369, 2020.

Abstract

We consider Inverse Reinforcement Learning (IRL) about multiple intentions, \ie the problem of estimating the unknown reward functions optimized by a group of experts that demonstrate optimal behaviors. Most of the existing algorithms either require access to a model of the environment or need to repeatedly compute the optimal policies for the hypothesized rewards. However, these requirements are rarely met in real-world applications, in which interacting with the environment can be expensive or even dangerous. In this paper, we address the IRL about multiple intentions in a fully model-free and batch setting. We first cast the single IRL problem as a constrained likelihood maximization and then we use this formulation to cluster agents based on the likelihood of the assignment. In this way, we can efficiently solve, without interactions with the environment, both the IRL and the clustering problem. Finally, we evaluate the proposed methodology on simulated domains and on a real-world social-network application.

Cite this Paper


BibTeX
@InProceedings{pmlr-v108-ramponi20a, title = {Truly Batch Model-Free Inverse Reinforcement Learning about Multiple Intentions}, author = {Ramponi, Giorgia and Likmeta, Amarildo and Metelli, Alberto Maria and Tirinzoni, Andrea and Restelli, Marcello}, booktitle = {Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics}, pages = {2359--2369}, year = {2020}, editor = {Silvia Chiappa and Roberto Calandra}, volume = {108}, series = {Proceedings of Machine Learning Research}, month = {26--28 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v108/ramponi20a/ramponi20a.pdf}, url = { http://proceedings.mlr.press/v108/ramponi20a.html }, abstract = {We consider Inverse Reinforcement Learning (IRL) about multiple intentions, \ie the problem of estimating the unknown reward functions optimized by a group of experts that demonstrate optimal behaviors. Most of the existing algorithms either require access to a model of the environment or need to repeatedly compute the optimal policies for the hypothesized rewards. However, these requirements are rarely met in real-world applications, in which interacting with the environment can be expensive or even dangerous. In this paper, we address the IRL about multiple intentions in a fully model-free and batch setting. We first cast the single IRL problem as a constrained likelihood maximization and then we use this formulation to cluster agents based on the likelihood of the assignment. In this way, we can efficiently solve, without interactions with the environment, both the IRL and the clustering problem. Finally, we evaluate the proposed methodology on simulated domains and on a real-world social-network application.} }
Endnote
%0 Conference Paper %T Truly Batch Model-Free Inverse Reinforcement Learning about Multiple Intentions %A Giorgia Ramponi %A Amarildo Likmeta %A Alberto Maria Metelli %A Andrea Tirinzoni %A Marcello Restelli %B Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2020 %E Silvia Chiappa %E Roberto Calandra %F pmlr-v108-ramponi20a %I PMLR %P 2359--2369 %U http://proceedings.mlr.press/v108/ramponi20a.html %V 108 %X We consider Inverse Reinforcement Learning (IRL) about multiple intentions, \ie the problem of estimating the unknown reward functions optimized by a group of experts that demonstrate optimal behaviors. Most of the existing algorithms either require access to a model of the environment or need to repeatedly compute the optimal policies for the hypothesized rewards. However, these requirements are rarely met in real-world applications, in which interacting with the environment can be expensive or even dangerous. In this paper, we address the IRL about multiple intentions in a fully model-free and batch setting. We first cast the single IRL problem as a constrained likelihood maximization and then we use this formulation to cluster agents based on the likelihood of the assignment. In this way, we can efficiently solve, without interactions with the environment, both the IRL and the clustering problem. Finally, we evaluate the proposed methodology on simulated domains and on a real-world social-network application.
APA
Ramponi, G., Likmeta, A., Metelli, A.M., Tirinzoni, A. & Restelli, M.. (2020). Truly Batch Model-Free Inverse Reinforcement Learning about Multiple Intentions. Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 108:2359-2369 Available from http://proceedings.mlr.press/v108/ramponi20a.html .

Related Material