Asynchronous Methods for Deep Reinforcement Learning

02/04/2016
by   Volodymyr Mnih, et al.
0

We propose a conceptually simple and lightweight framework for deep reinforcement learning that uses asynchronous gradient descent for optimization of deep neural network controllers. We present asynchronous variants of four standard reinforcement learning algorithms and show that parallel actor-learners have a stabilizing effect on training allowing all four methods to successfully train neural network controllers. The best performing method, an asynchronous variant of actor-critic, surpasses the current state-of-the-art on the Atari domain while training for half the time on a single multi-core CPU instead of a GPU. Furthermore, we show that asynchronous actor-critic succeeds on a wide variety of continuous motor control problems as well as on a new task of navigating random 3D mazes using a visual input.

READ FULL TEXT

page 8

page 17

research
05/19/2017

Atari games and Intel processors

The asynchronous nature of the state-of-the-art reinforcement learning a...
research
12/21/2020

Combining Deep Reinforcement Learning And Local Control For The Acrobot Swing-up And Balance Task

In this work we present a novel extension of soft actor critic, a state ...
research
10/28/2019

Neural Architecture Evolution in Deep Reinforcement Learning for Continuous Control

Current Deep Reinforcement Learning algorithms still heavily rely on han...
research
08/19/2017

A Brief Survey of Deep Reinforcement Learning

Deep reinforcement learning is poised to revolutionise the field of AI a...
research
08/13/2018

Visual Sensor Network Reconfiguration with Deep Reinforcement Learning

We present an approach for reconfiguration of dynamic visual sensor netw...
research
06/09/2019

Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning

Multi-simulator training has contributed to the recent success of Deep R...
research
05/25/2020

Gradient Monitored Reinforcement Learning

This paper presents a novel neural network training approach for faster ...

Please sign up or login with your details

Forgot password? Click here to reset