Are Gradient-based Saliency Maps Useful In Deep Reinforcement Learning?

Abstract

Deep Reinforcement Learning (DRL) connects the classic Reinforcement Learning algorithms with Deep Neural Networks. A problem in DRL is that CNNs are black-boxes and it is hard to understand the decision-making process of agents. In order to be able to use RL agents in highly dangerous environments for humans and machines, the developer needs a debugging tool to assure that the agent does what is expected. Currently, rewards are primarily used to interpret how well an agent is learning. However, this can lead to deceptive conclusions if the agent receives more rewards by memorizing a policy and not learning to respond to the environment. In this work, it is shown that this problem can be recognized with the help of gradient visualization techniques. This work brings some of the best-known visualization methods from the field of image classification to the area of Deep Reinforcement Learning. Furthermore, two new visualization techniques have been developed, one of which provides partic

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyrosynski2020are

Related papers

• Exploratory Not Explanatory: Counterfactual Analysis Of Saliency Maps For Deep Reinforcement Learning (2019)0.00
• Visualizing And Understanding Atari Agents (2017)0.00
• Look Where You Look! Saliency-guided Q-networks For Generalization In Visual Reinforcement Learning (2022)0.00
• Machine Versus Human Attention In Deep Reinforcement Learning Tasks (2020)0.00
• Benchmarking Perturbation-based Saliency Maps For Explaining Atari Agents (2021)0.00
• Explain Your Move: Understanding Agent Actions Using Specific And Relevant Feature Attribution (2019)0.00
• Visual Explanation Using Attention Mechanism In Actor-critic-based Deep Reinforcement Learning (2021)10.21
• Learning To Identify Critical States For Reinforcement Learning From Videos (2023)8.76