DeepAI AI Chat
Log In Sign Up

Rainbow: Combining Improvements in Deep Reinforcement Learning

by   Matteo Hessel, et al.

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.


page 1

page 2

page 3

page 4


PPO Dash: Improving Generalization in Deep Reinforcement Learning

Deep reinforcement learning is prone to overfitting, and traditional ben...

Spectral Normalisation for Deep Reinforcement Learning: an Optimisation Perspective

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

Biologically inspired architectures for sample-efficient deep reinforcement learning

Deep reinforcement learning requires a heavy price in terms of sample ef...

Attend2Pack: Bin Packing through Deep Reinforcement Learning with Attention

This paper seeks to tackle the bin packing problem (BPP) through a learn...

Deep Reinforcement Learning with Feedback-based Exploration

Deep Reinforcement Learning has enabled the control of increasingly comp...

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

Deep neuroevolution and deep Reinforcement Learning have received a lot ...

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

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

Code Repositories