SAAC: Safe Reinforcement Learning as an Adversarial Game of Actor-Critics - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

SAAC: Safe Reinforcement Learning as an Adversarial Game of Actor-Critics

Debabrota Basu

Résumé

Although Reinforcement Learning (RL) is effective for sequential decision-making problems under uncertainty, it still fails to thrive in real-world systems where risk or safety is a binding constraint. In this paper, we formulate the RL problem with safety constraints as a non-zero-sum game. While deployed with maximum entropy RL, this formulation leads to a safe adversarially guided soft actor-critic framework, called SAAC. In SAAC, the adversary aims to break the safety constraint while the RL agent aims to maximize the constrained value function given the adversary's policy. The safety constraint on the agent's value function manifests only as a repulsion term between the agent's and the adversary's policies. Unlike previous approaches, SAAC can address different safety criteria such as safe exploration, mean-variance risk sensitivity, and CVaR-like coherent risk sensitivity. We illustrate the design of the adversary for these constraints. Then, in each of these variations, we show the agent differentiates itself from the adversary's unsafe actions in addition to learning to solve the task. Finally, for challenging continuous control tasks, we demonstrate that SAAC achieves faster convergence, better efficiency, and fewer failures to satisfy the safety constraints than risk-averse distributional RL and risk-neutral soft actor-critic algorithms.
Fichier principal
Vignette du fichier
saac arxiv.pdf (1.13 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03771734 , version 1 (07-09-2022)

Licence

Paternité - Pas d'utilisation commerciale

Identifiants

Citer

Yannis Flet-Berliac, Debabrota Basu. SAAC: Safe Reinforcement Learning as an Adversarial Game of Actor-Critics. RLDM 2022 - The Multi-disciplinary Conference on Reinforcement Learning and Decision Making, Jun 2022, Providence, United States. ⟨hal-03771734⟩
34 Consultations
75 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More