Safety Aware Reinforcement Learning (SARL)

Abstract

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 w

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymiret2020safety

Related papers

• Context-aware Safe Reinforcement Learning For Non-stationary Environments (2021)9.76
• Safety Correction From Baseline: Towards The Risk-aware Policy In Robotics Via Dual-agent Reinforcement Learning (2022)3.58
• Actsafe: Active Exploration With Safety Constraints For Reinforcement Learning (2024)0.00
• Omnisafe: An Infrastructure For Accelerating Safe Reinforcement Learning Research (2023)0.00
• Reinforcement Learning By Guided Safe Exploration (2023)5.24
• Safe Multi-agent Reinforcement Learning With Convergence To Generalized Nash Equilibrium (2024)0.00
• Learning Safe Policies With Expert Guidance (2018)0.00
• Reinforcement Learning With Adaptive Regularization For Safe Control Of Critical Systems (2024)0.00