Safe Reinforcement Learning by Imagining the Near Future
Safe reinforcement learning is a promising path toward applying reinforcement learning algorithms to real-world problems, where suboptimal behaviors may lead to actual negative consequences. In this work, we focus on the setting where unsafe states can be avoided by planning ahead a short time into the future. In this setting, a model-based agent with a sufficiently accurate model can avoid unsafe states. We devise a model-based algorithm that heavily penalizes unsafe trajectories, and derive guarantees that our algorithm can avoid unsafe states under certain assumptions. Experiments demonstrate that our algorithm can achieve competitive rewards with fewer safety violations in several continuous control tasks.
Code (1)
Tasks
continuous-controlContinuous Controlreinforcement-learningReinforcement LearningReinforcement Learning (RL)Safe Reinforcement LearningSimilar Papers 제목 키워드 기반
ProSpec RL: Plan Ahead, then Execute
Imagining potential outcomes of actions before execution helps agents make more informed decisions, a prospective thinking ability fundamental to human cognition. However, mainstream model-free Reinforcement Learning (RL…
Model Predictive ControlReinforcement Learning (RL)Efficient Intrinsically Motivated Robotic Grasping with Learning-Adaptive Imagination in Latent Space
Combining model-based and model-free deep reinforcement learning has shown great promise for improving sample efficiency on complex control tasks while still retaining high performance. Incorporating imagination is a rec…
Deep Reinforcement LearningReinforcement LearningRobotic GraspingCoimagining the Future of Voice Assistants with Cultural Sensitivity
Voice assistants (VAs) are becoming a feature of our everyday life. Yet, the user experience (UX) is often limited, leading to underuse, disengagement, and abandonment. Co-designing interactions for VAs with potential en…
SensitivityParenting: Safe Reinforcement Learning from Human Input
Autonomous agents trained via reinforcement learning present numerous safety concerns: reward hacking, negative side effects, and unsafe exploration, among others. In the context of near-future autonomous agents, operati…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Safe Reinforcement LearningSafe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithms
Safe exploration is essential for the practical use of reinforcement learning (RL) in many real-world scenarios. In this paper, we present a generalized safe exploration (GSE) problem as a unified formulation of common s…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Safe Exploration