Rainbow: Combining Improvements in Deep Reinforcement Learning

10/06/2017
by   Matteo Hessel, et al.
0

The deep reinforcement learning community has made several independent improvements to the DQN algorithm. However, it is unclear which of these extensions are complementary and can be fruitfully combined. This paper examines six extensions to the DQN algorithm and empirically studies their combination. Our experiments show that the combination provides state-of-the-art performance on the Atari 2600 benchmark, both in terms of data efficiency and final performance. We also provide results from a detailed ablation study that shows the contribution of each component to overall performance.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/15/2019

PPO Dash: Improving Generalization in Deep Reinforcement Learning

Deep reinforcement learning is prone to overfitting, and traditional ben...
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...
research
11/25/2019

Biologically inspired architectures for sample-efficient deep reinforcement learning

Deep reinforcement learning requires a heavy price in terms of sample ef...
research
07/09/2021

Attend2Pack: Bin Packing through Deep Reinforcement Learning with Attention

This paper seeks to tackle the bin packing problem (BPP) through a learn...
research
03/14/2019

Deep Reinforcement Learning with Feedback-based Exploration

Deep Reinforcement Learning has enabled the control of increasingly comp...
research
03/26/2022

Combining Evolution and Deep Reinforcement Learning for Policy Search: a Survey

Deep neuroevolution and deep Reinforcement Learning have received a lot ...
research
11/11/2018

An Initial Attempt of Combining Visual Selective Attention with Deep Reinforcement Learning

Visual attention serves as a means of feature selection mechanism in the...

Please sign up or login with your details

Forgot password? Click here to reset