paper-with-me

홈 › Papers

Safety Aware Reinforcement Learning (SARL)

2020-10-06 · Santiago Miret, Somdeb Majumdar, Carroll Wainwright

As reinforcement learning agents become increasingly integrated into complex, real-world environments, designing for safety becomes a critical consideration. We specifically focus on researching scenarios where agents can cause undesired side effects while executing a policy on a primary task. Since one can define multiple tasks for a given environment dynamics, there are two important challenges. First, we need to abstract the concept of safety that applies broadly to that environment independent of the specific task being executed. Second, we need a mechanism for the abstracted notion of safety to modulate the actions of agents executing different policies to minimize their side-effects. In this work, we propose Safety Aware Reinforcement Learning (SARL) - a framework where a virtual safe agent modulates the actions of a main reward-based agent to minimize side effects. The safe agent learns a task-independent notion of safety for a given environment. The main agent is then trained with a regularization loss given by the distance between the native action probabilities of the two agents. Since the safe agent effectively abstracts a task-independent notion of safety via its action probabilities, it can be ported to modulate multiple policies solving different tasks within the given environment without further training. We contrast this with solutions that rely on task-specific regularization metrics and test our framework on the SafeLife Suite, based on Conway's Game of Life, comprising a number of complex tasks in dynamic environments. We show that our solution is able to match the performance of solutions that rely on task-specific side-effect penalties on both the primary and safety objectives while additionally providing the benefit of generalizability and portability.

📄 PDF Abstract BibTeX arXiv:2010.02846

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Long-term Safe Reinforcement Learning with Binary Feedback

2024-01-08 · Akifumi Wachi, Wataru Hashimoto, Kazumune Hashimoto

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 …

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Safe Reinforcement Learning

SARL*: Deep Reinforcement Learning based Human-Aware Navigation for Mobile Robot in Indoor Environments

2020-01-20 · Keyu Li, Yangxin Xu, Jiankun Wang, Max Q.-H. Meng

In a human-robot coexisting environment, reaching the goal position safely and efficiently is essential for a mobile service robot. In this paper, we present an advanced version of the Socially Attentive Reinforcement Le…

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

SARL: Label-Free Reinforcement Learning by Rewarding Reasoning Topology

2026-03-30 · Yifan Wang, Bolian Li, David Cho, Ruqi Zhang 외 arxiv

Reinforcement learning is critical to improving large reasoning models, but its success relies heavily on verifiable rewards (RLVR), making it hard to use in open-ended domains where correctness is ambiguous and cannot b…

Reinforcement Learning

ViSaRL: Visual Reinforcement Learning Guided by Human Saliency

2024-03-16 · Anthony Liang, Jesse Thomason, Erdem Biyik

Training robots to perform complex control tasks from high-dimensional pixel input using reinforcement learning (RL) is sample-inefficient, because image observations are comprised primarily of task-irrelevant informatio…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Robot Manipulation

Reducing Cognitive Overhead in Tool Use via Multi-Small-Agent Reinforcement Learning

2025-08-12 · Dayu Wang, Jiaye Yang, Weikang Li, Jiahui Liang 외 arxiv

Recent advances in multi-agent systems highlight the potential of specialized small agents that collaborate via division of labor. Existing tool-integrated reasoning systems, however, often follow a single-agent paradigm…

Reinforcement Learning