Entropy-Aware Model Initialization for Effective Exploration in Deep Reinforcement Learning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Jang, Sooyoung, Kim, Hyung-Il
Natura: Preprint
Pubblicazione: 2021
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916626239062016
author Jang, Sooyoung
Kim, Hyung-Il
author_facet Jang, Sooyoung
Kim, Hyung-Il
contents Encouraging exploration is a critical issue in deep reinforcement learning. We investigate the effect of initial entropy that significantly influences the exploration, especially at the earlier stage. Our main observations are as follows: 1) low initial entropy increases the probability of learning failure, and 2) this initial entropy is biased towards a low value that inhibits exploration. Inspired by the investigations, we devise entropy-aware model initialization, a simple yet powerful learning strategy for effective exploration. We show that the devised learning strategy significantly reduces learning failures and enhances performance, stability, and learning speed through experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2108_10533
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Entropy-Aware Model Initialization for Effective Exploration in Deep Reinforcement Learning
Jang, Sooyoung
Kim, Hyung-Il
Machine Learning
Artificial Intelligence
Encouraging exploration is a critical issue in deep reinforcement learning. We investigate the effect of initial entropy that significantly influences the exploration, especially at the earlier stage. Our main observations are as follows: 1) low initial entropy increases the probability of learning failure, and 2) this initial entropy is biased towards a low value that inhibits exploration. Inspired by the investigations, we devise entropy-aware model initialization, a simple yet powerful learning strategy for effective exploration. We show that the devised learning strategy significantly reduces learning failures and enhances performance, stability, and learning speed through experiments.
title Entropy-Aware Model Initialization for Effective Exploration in Deep Reinforcement Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2108.10533