Explain Your Move: Understanding Agent Actions Using Specific And Relevant Feature Attribution

Abstract

As deep reinforcement learning (RL) is applied to more tasks, there is a need to visualize and understand the behavior of learned agents. Saliency maps explain agent behavior by highlighting the features of the input state that are most relevant for the agent in taking an action. Existing perturbation-based approaches to compute saliency often highlight regions of the input that are not relevant to the action taken by the agent. Our proposed approach, SARFA (Specific and Relevant Feature Attribution), generates more focused saliency maps by balancing two aspects (specificity and relevance) that capture different desiderata of saliency. The first captures the impact of perturbation on the relative expected reward of the action to be explained. The second downweighs irrelevant features that alter the relative expected rewards of actions other than the action to be explained. We compare SARFA with existing approaches on agents trained to play board games (Chess and Go) and Atari games (Br

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keypuri2019explain

Related papers

• Visualizing And Understanding Atari Agents (2017)0.00
• Benchmarking Perturbation-based Saliency Maps For Explaining Atari Agents (2021)0.00
• Exploratory Not Explanatory: Counterfactual Analysis Of Saliency Maps For Deep Reinforcement Learning (2019)0.00
• Local And Global Explanations Of Agent Behavior: Integrating Strategy Summaries With Saliency Maps (2020)11.85
• Reconstructing Actions To Explain Deep Reinforcement Learning (2020)0.00
• Machine Versus Human Attention In Deep Reinforcement Learning Tasks (2020)0.00
• Explaining Deep Reinforcement Learning Agents In The Atari Domain Through A Surrogate Model (2021)0.00
• Learn To Interpret Atari Agents (2018)0.00