Assessing and Accelerating Coverage in Deep Reinforcement Learning

12/01/2020
by   Arpan Kusari, et al.
0

Current deep reinforcement learning (DRL) algorithms utilize randomness in simulation environments to assume complete coverage in the state space. However, particularly in high dimensions, relying on randomness may lead to gaps in coverage of the trained DRL neural network model, which in turn may lead to drastic and often fatal real-world situations. To the best of the author's knowledge, the assessment of coverage for DRL is lacking in current research literature. Therefore, in this paper, a novel measure, Approximate Pseudo-Coverage (APC), is proposed for assessing the coverage in DRL applications. We propose to calculate APC by projecting the high dimensional state space on to a lower dimensional manifold and quantifying the occupied space. Furthermore, we utilize an exploration-exploitation strategy for coverage maximization using Rapidly-Exploring Random Tree (RRT). The efficacy of the assessment and the acceleration of coverage is demonstrated on standard tasks such as Cartpole, highway-env.

READ FULL TEXT

page 4

page 5

research
04/05/2018

A Human Mixed Strategy Approach to Deep Reinforcement Learning

In 2015, Google's DeepMind announced an advancement in creating an auton...
research
05/19/2021

Improved Exploring Starts by Kernel Density Estimation-Based State-Space Coverage Acceleration in Reinforcement Learning

Reinforcement learning (RL) is currently a popular research topic in con...
research
11/22/2020

Distributed Deep Reinforcement Learning: An Overview

Deep reinforcement learning (DRL) is a very active research area. Howeve...
research
04/29/2021

Hypernetwork Dismantling via Deep Reinforcement Learning

Network dismantling aims to degrade the connectivity of a network by rem...
research
08/27/2022

Unsupervised Representation Learning in Deep Reinforcement Learning: A Review

This review addresses the problem of learning abstract representations o...
research
06/08/2022

Action Noise in Off-Policy Deep Reinforcement Learning: Impact on Exploration and Performance

Many deep reinforcement learning algorithms rely on simple forms of expl...
research
02/22/2022

Cellular Network Capacity and Coverage Enhancement with MDT Data and Deep Reinforcement Learning

Recent years witnessed a remarkable increase in the availability of data...

Please sign up or login with your details

Forgot password? Click here to reset