Explainable Reinforcement Learning for Longitudinal Control
Deep Reinforcement Learning (DRL) has the potential to surpass the existing state of the art in various practical applications. However, as long as learned strategies and performed decisions are difficult to interpret, DRL will not find its way into safety-relevant fields of application. SHAP values are an approach to overcome this problem. It is expected that the addition of these values to DRL provides an improved understanding of the learned action-selection policy. In this paper, the application of a SHAP method for DRL is demonstrated by means of the OpenAI Gym LongiControl Environment. In this problem, the agent drives an autonomous vehicle under consideration of speed limits in a single lane route. The controls learned with a DDPG algorithm are interpreted by a novel approach combining learned actions and SHAP values. The proposed RL-SHAP representation makes it possible to observe in every time step which features have a positive or negative effect on the selected action and which influences are negligible. The results show that RL-SHAP values are a suitable approach to interpret the decisions of the agent.
Code (1)
Tasks
Deep Reinforcement LearningOpenAI Gymreinforcement-learningReinforcement LearningReinforcement Learning (RL)Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Longitudinal Deep Truck: Deep learning and deep reinforcement learning for modeling and control of longitudinal dynamics of heavy duty trucks
Heavy duty truck mechanical configuration is often tailor designed and built for specific truck mission requirements. This renders the precise derivation of analytical dynamical models and controls for these trucks from …
Deep Reinforcement LearningReinforcement Learning (RL)LongiControl: A Reinforcement Learning Environment for Longitudinal Vehicle Control
Reinforcement Learning (RL) might be very promising for solving a variety of challenges in the field of autonomous driving due to its ability to find long-term oriented solutions in complex decision scenarios. For traini…
Autonomous DrivingOpenAI Gymreinforcement-learningReinforcement Learning+1Longitudinal Dynamic versus Kinematic Models for Car-Following Control Using Deep Reinforcement Learning
The majority of current studies on autonomous vehicle control via deep reinforcement learning (DRL) utilize point-mass kinematic models, neglecting vehicle dynamics which includes acceleration delay and acceleration comm…
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Deep Reinforcement Learning for Advanced Longitudinal Control and Collision Avoidance in High-Risk Driving Scenarios
Existing Advanced Driver Assistance Systems primarily focus on the vehicle directly ahead, often overlooking potential risks from following vehicles. This oversight can lead to ineffective handling of high risk situation…
Collision AvoidanceDeep Reinforcement LearningReLMXEL: Adaptive RL-Based Memory Controller with Explainable Energy and Latency Optimization
Reducing latency and energy consumption is critical to improving the efficiency of memory systems in modern computing. This work introduces ReLMXEL (Reinforcement Learning for Memory Controller with Explainable Energy an…
Reinforcement Learning