Reward (Mis)design for Autonomous Driving
This article considers the problem of diagnosing certain common errors in reward design. Its insights are also applicable to the design of cost functions and performance metrics more generally. To diagnose common errors, we develop 8 simple sanity checks for identifying flaws in reward functions. These sanity checks are applied to reward functions from past work on reinforcement learning (RL) for autonomous driving (AD), revealing near-universal flaws in reward design for AD that might also exist pervasively across reward design for other tasks. Lastly, we explore promising directions that may aid the design of reward functions for AD in subsequent research, following a process of inquiry that can be adapted to other domains.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous Drivingreinforcement-learningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
LORD: Large Models based Opposite Reward Design for Autonomous Driving
Reinforcement learning (RL) based autonomous driving has emerged as a promising alternative to data-driven imitation learning approaches. However, crafting effective reward functions for RL poses challenges due to the co…
Autonomous DrivingImitation LearningReinforcement Learning (RL)Risk-Aware Reward Shaping of Reinforcement Learning Agents for Autonomous Driving
Reinforcement learning (RL) is an effective approach to motion planning in autonomous driving, where an optimal driving policy can be automatically learned using the interaction data with the environment. Nevertheless, t…
Autonomous DrivingMotion PlanningOpenAI Gymreinforcement-learning+1CLIP-RLDrive: Human-Aligned Autonomous Driving via CLIP-Based Reward Shaping in Reinforcement Learning
This paper presents CLIP-RLDrive, a new reinforcement learning (RL)-based framework for improving the decision-making of autonomous vehicles (AVs) in complex urban driving scenarios, particularly in unsignalized intersec…
Autonomous DrivingAutonomous VehiclesDecision MakingReinforcement Learning (RL)Generating and Evolving Reward Functions for Highway Driving with Large Language Models
Reinforcement Learning (RL) plays a crucial role in advancing autonomous driving technologies by maximizing reward functions to achieve the optimal policy. However, crafting these reward functions has been a complex, man…
Autonomous DrivingReinforcement Learning (RL)AED: Automatic Discovery of Effective and Diverse Vulnerabilities for Autonomous Driving Policy with Large Language Models
Assessing the safety of autonomous driving policy is of great importance, and reinforcement learning (RL) has emerged as a powerful method for discovering critical vulnerabilities in driving policies. However, existing R…
Autonomous DrivingReinforcement Learning (RL)