Distilling Deep RL Models Into Interpretable Neuro-Fuzzy Systems

09/07/2022
by   Arne Gevaert, et al.
4

Deep Reinforcement Learning uses a deep neural network to encode a policy, which achieves very good performance in a wide range of applications but is widely regarded as a black box model. A more interpretable alternative to deep networks is given by neuro-fuzzy controllers. Unfortunately, neuro-fuzzy controllers often need a large number of rules to solve relatively simple tasks, making them difficult to interpret. In this work, we present an algorithm to distill the policy from a deep Q-network into a compact neuro-fuzzy controller. This allows us to train compact neuro-fuzzy controllers through distillation to solve tasks that they are unable to solve directly, combining the flexibility of deep reinforcement learning and the interpretability of compact rule bases. We demonstrate the algorithm on three well-known environments from OpenAI Gym, where we nearly match the performance of a DQN agent using only 2 to 6 fuzzy rules.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/17/2023

A Genetic Fuzzy System for Interpretable and Parsimonious Reinforcement Learning Policies

Reinforcement learning (RL) is experiencing a resurgence in research int...
research
05/07/2023

Opening the TAR Black Box: Developing an Interpretable System for eDiscovery Using the Fuzzy ARTMAP Neural Network

This foundational research provides additional support for using the Fuz...
research
05/25/2019

Deep Image Feature Learning with Fuzzy Rules

The methods of extracting image features are the key to many image proce...
research
04/29/2018

Generating Interpretable Fuzzy Controllers using Particle Swarm Optimization and Genetic Programming

Autonomously training interpretable control strategies, called policies,...
research
12/23/2019

Learning an Interpretable Traffic Signal Control Policy

Signalized intersections are managed by controllers that assign right of...
research
06/10/2021

Synthesising Reinforcement Learning Policies through Set-Valued Inductive Rule Learning

Today's advanced Reinforcement Learning algorithms produce black-box pol...
research
10/10/2020

Distilling a Deep Neural Network into a Takagi-Sugeno-Kang Fuzzy Inference System

Deep neural networks (DNNs) demonstrate great success in classification ...

Please sign up or login with your details

Forgot password? Click here to reset