Communication Dans Un Congrès Année : 2024

Approaching Single-Episode Survival Reinforcement Learning with Safety-Threshold Q-Learning

Résumé

Survival Reinforcement Learning is a specific type of RL problem constrained by a risk of ruin. The underlying stochastic sequential decision process with which the agent interacts includes a budget that evolves over time with the received rewards and must remain positive throughout its entire lifetime. The goal is to find a good trade-off between exploration, exploitation, and safety during a single learning episode, maximizing rewards while managing the available budget to minimize the probability of ruin. Existing approaches do not provide satisfactory solutions to this problem. This paper introduces the safety-threshold heuristic, which is used to extend the standard Q-Learning method. A simulated grid environment is used to evaluate its performance.
Fichier principal
Vignette du fichier
2024___OLA___A3R__CR_proceedings_.pdf (789) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04699264 , version 1 (16-09-2024)

Identifiants

  • HAL Id : hal-04699264 , version 1

Citer

Filipo Studzinski Perotto, Melvine Nargeot, Aymane Ouahbi. Approaching Single-Episode Survival Reinforcement Learning with Safety-Threshold Q-Learning. International Conference on Optimization and Learning (OLA), May 2024, Dubrovnik, Croatia. ⟨hal-04699264⟩
25 Consultations
24 Téléchargements

Partager

More