Generating Explanations from Deep Reinforcement Learning Using Episodic Memory

by   Sam Blakeman, et al.
Birkbeck, University of London

Deep Reinforcement Learning (RL) involves the use of Deep Neural Networks (DNNs) to make sequential decisions in order to maximize reward. For many tasks the resulting sequence of actions produced by a Deep RL policy can be long and difficult to understand for humans. A crucial component of human explanations is selectivity, whereby only key decisions and causes are recounted. Imbuing Deep RL agents with such an ability would make their resulting policies easier to understand from a human perspective and generate a concise set of instructions to aid the learning of future agents. To this end we use a Deep RL agent with an episodic memory system to identify and recount key decisions during policy execution. We show that these decisions form a short, human readable explanation that can also be used to speed up the learning of naive Deep RL agents in an algorithm-independent manner.


page 4

page 5

page 6

page 9

page 10

page 11

page 15

page 16


Decisions that Explain Themselves: A User-Centric Deep Reinforcement Learning Explanation System

With deep reinforcement learning (RL) systems like autonomous driving be...

Towards Behavior-Level Explanation for Deep Reinforcement Learning

While Deep Neural Networks (DNNs) are becoming the state-of-the-art for ...

Human versus Machine Attention in Deep Reinforcement Learning Tasks

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

Deep Q-Networks for Accelerating the Training of Deep Neural Networks

In this paper, we propose a principled deep reinforcement learning (RL) ...

Measuring and Characterizing Generalization in Deep Reinforcement Learning

Deep reinforcement-learning methods have achieved remarkable performance...

Acme: A Research Framework for Distributed Reinforcement Learning

Deep reinforcement learning has led to many recent-and groundbreaking-ad...

RAPID-RL: A Reconfigurable Architecture with Preemptive-Exits for Efficient Deep-Reinforcement Learning

Present-day Deep Reinforcement Learning (RL) systems show great promise ...

Please sign up or login with your details

Forgot password? Click here to reset