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 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.

References in corpus (12)

• Playing Atari with Deep Reinforcement Learning
• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
• Multi-Task Learning as Multi-Objective Optimization
• How (not) to Train your Generative Model: Scheduled Sampling, Likelihood, Adversary?
• Chip Placement with Deep Reinforcement Learning
• Effective Diversity in Population Based Reinforcement Learning
• Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences
• Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings
• Penalizing side effects using stepwise relative reachability
• Safe Predictors for Enforcing Input-Output Specifications
• Learning to Score Behaviors for Guided Policy Optimization
• Avoiding Side Effects in Complex Environments