AI Chat AI Image Generator AI Video Text to Speech

Faster Deep Q-learning using Neural Episodic Control

01/06/2018

∙

by Daichi Nishio, et al.

∙

∙

The Research on deep reinforcement learning to estimate Q-value by deep learning has been active in recent years. In deep reinforcement learning, it is important to efficiently learn the experiences that a agent has collected by exploring the environment. In this research, we propose NEC2DQN that improves learning speed of a algorithm with poor sample efficiency by using a algorithm with good one at the beginning of learning, and we demonstrate it in experiments.

Daichi Nishio
4 publications
Satoshi Yamane
5 publications

page 3

page 5

research

∙ 12/17/2017

Towards a Deep Reinforcement Learning Approach for Tower Line Wars

There have been numerous breakthroughs with reinforcement learning in th...

0 Per-Arne Andersen, et al. ∙

research

∙ 08/04/2019

Deep Reinforcement Learning in System Optimization

The recent advancements in deep reinforcement learning have opened new h...

6 Ameer Haj-Ali, et al. ∙

research

∙ 10/15/2018

Using Deep Reinforcement Learning for the Continuous Control of Robotic Arms

Deep reinforcement learning enables algorithms to learn complex behavior...

0 Winfried Lötzsch, et al. ∙

research

∙ 04/23/2018

Towards Symbolic Reinforcement Learning with Common Sense

Deep Reinforcement Learning (deep RL) has made several breakthroughs in ...

0 Artur d'Avila Garcez, et al. ∙

research

∙ 04/07/2023

A modular framework for stabilizing deep reinforcement learning control

We propose a framework for the design of feedback controllers that combi...

0 Nathan P. Lawrence, et al. ∙

research

∙ 02/07/2022

Optimizing Warfarin Dosing using Deep Reinforcement Learning

Warfarin is a widely used anticoagulant, and has a narrow therapeutic ra...

0 Sadjad Anzabi Zadeh, et al. ∙

research

∙ 05/11/2021

Spectral Normalisation for Deep Reinforcement Learning: an Optimisation Perspective

Most of the recent deep reinforcement learning advances take an RL-centr...

7 Florin Gogianu, et al. ∙