Salvato in:
Dettagli Bibliografici
Autori principali: Wachi, Akifumi, Hashimoto, Wataru, Hashimoto, Kazumune
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2401.03786
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916088009195520
author Wachi, Akifumi
Hashimoto, Wataru
Hashimoto, Kazumune
author_facet Wachi, Akifumi
Hashimoto, Wataru
Hashimoto, Kazumune
contents Safety is an indispensable requirement for applying reinforcement learning (RL) to real problems. Although there has been a surge of safe RL algorithms proposed in recent years, most existing work typically 1) relies on receiving numeric safety feedback; 2) does not guarantee safety during the learning process; 3) limits the problem to a priori known, deterministic transition dynamics; and/or 4) assume the existence of a known safe policy for any states. Addressing the issues mentioned above, we thus propose Long-term Binaryfeedback Safe RL (LoBiSaRL), a safe RL algorithm for constrained Markov decision processes (CMDPs) with binary safety feedback and an unknown, stochastic state transition function. LoBiSaRL optimizes a policy to maximize rewards while guaranteeing a long-term safety that an agent executes only safe state-action pairs throughout each episode with high probability. Specifically, LoBiSaRL models the binary safety function via a generalized linear model (GLM) and conservatively takes only a safe action at every time step while inferring its effect on future safety under proper assumptions. Our theoretical results show that LoBiSaRL guarantees the long-term safety constraint, with high probability. Finally, our empirical results demonstrate that our algorithm is safer than existing methods without significantly compromising performance in terms of reward.
format Preprint
id arxiv_https___arxiv_org_abs_2401_03786
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Long-term Safe Reinforcement Learning with Binary Feedback
Wachi, Akifumi
Hashimoto, Wataru
Hashimoto, Kazumune
Machine Learning
Artificial Intelligence
Robotics
Safety is an indispensable requirement for applying reinforcement learning (RL) to real problems. Although there has been a surge of safe RL algorithms proposed in recent years, most existing work typically 1) relies on receiving numeric safety feedback; 2) does not guarantee safety during the learning process; 3) limits the problem to a priori known, deterministic transition dynamics; and/or 4) assume the existence of a known safe policy for any states. Addressing the issues mentioned above, we thus propose Long-term Binaryfeedback Safe RL (LoBiSaRL), a safe RL algorithm for constrained Markov decision processes (CMDPs) with binary safety feedback and an unknown, stochastic state transition function. LoBiSaRL optimizes a policy to maximize rewards while guaranteeing a long-term safety that an agent executes only safe state-action pairs throughout each episode with high probability. Specifically, LoBiSaRL models the binary safety function via a generalized linear model (GLM) and conservatively takes only a safe action at every time step while inferring its effect on future safety under proper assumptions. Our theoretical results show that LoBiSaRL guarantees the long-term safety constraint, with high probability. Finally, our empirical results demonstrate that our algorithm is safer than existing methods without significantly compromising performance in terms of reward.
title Long-term Safe Reinforcement Learning with Binary Feedback
topic Machine Learning
Artificial Intelligence
Robotics
url https://arxiv.org/abs/2401.03786