DeepAI AI Chat
Log In Sign Up

Designing Interpretable Approximations to Deep Reinforcement Learning with Soft Decision Trees

by   Nathan Dahlin, et al.

In an ever expanding set of research and application areas, deep neural networks (DNNs) set the bar for algorithm performance. However, depending upon additional constraints such as processing power and execution time limits, or requirements such as verifiable safety guarantees, it may not be feasible to actually use such high-performing DNNs in practice. Many techniques have been developed in recent years to compress or distill complex DNNs into smaller, faster or more understandable models and controllers. This work seeks to provide a quantitative framework with metrics to systematically evaluate the outcome of such conversion processes, and identify reduced models that not only preserve a desired performance level, but also, for example, succinctly explain the latent knowledge represented by a DNN. We illustrate the effectiveness of the proposed approach on the evaluation of decision tree variants in the context of benchmark reinforcement learning tasks.


page 6

page 7

page 8

page 9


Strategy and Benchmark for Converting Deep Q-Networks to Event-Driven Spiking Neural Networks

Spiking neural networks (SNNs) have great potential for energy-efficient...

Towards Interpretable Deep Neural Networks: An Exact Transformation to Multi-Class Multivariate Decision Trees

Deep neural networks (DNNs) are commonly labelled as black-boxes lacking...

Exploring layerwise decision making in DNNs

While deep neural networks (DNNs) have become a standard architecture fo...

PoPS: Policy Pruning and Shrinking for Deep Reinforcement Learning

The recent success of deep neural networks (DNNs) for function approxima...

Rx-Caffe: Framework for evaluating and training Deep Neural Networks on Resistive Crossbars

Deep Neural Networks (DNNs) are widely used to perform machine learning ...

Approximating a deep reinforcement learning docking agent using linear model trees

Deep reinforcement learning has led to numerous notable results in robot...

Towards Scalable Verification of RL-Driven Systems

Deep neural networks (DNNs) have gained significant popularity in recent...