Visualizing and Understanding Atari Agents

by   Sam Greydanus, et al.

Deep reinforcement learning (deep RL) agents have achieved remarkable success in a broad range of game-playing and continuous control tasks. While these agents are effective at maximizing rewards, it is often unclear what strategies they use to do so. In this paper, we take a step toward explaining deep RL agents through a case study in three Atari 2600 environments. In particular, we focus on understanding agents in terms of their visual attentional patterns during decision making. To this end, we introduce a method for generating rich saliency maps and use it to explain 1) what strong agents attend to 2) whether agents are making decisions for the right or wrong reasons, and 3) how agents evolve during the learning phase. We also test our method on non-expert human subjects and find that it improves their ability to reason about these agents. Our techniques are general and, though we focus on Atari, our long-term objective is to produce tools that explain any deep RL policy.


page 2

page 5

page 6

page 7


Distributed Ensembles of Reinforcement Learning Agents for Electricity Control

Deep Reinforcement Learning (or just "RL") is gaining popularity for ind...

Human versus Machine Attention in Deep Reinforcement Learning Tasks

Deep reinforcement learning (RL) algorithms are powerful tools for solvi...

Benchmarking Perturbation-based Saliency Maps for Explaining Deep Reinforcement Learning Agents

Recent years saw a plethora of work on explaining complex intelligent ag...

Explainable Deep Reinforcement Learning Using Introspection in a Non-episodic Task

Explainable reinforcement learning allows artificial agents to explain t...

Explaining Reinforcement Learning to Mere Mortals: An Empirical Study

We present a user study to investigate the impact of explanations on non...

GridToPix: Training Embodied Agents with Minimal Supervision

While deep reinforcement learning (RL) promises freedom from hand-labele...

Please sign up or login with your details

Forgot password? Click here to reset