HackerPapers

arXiv:1710.02298cs.AI

Rainbow: Combining Improvements in Deep Reinforcement Learning

Matteo Hessel, Joseph Modayil, Hado van Hasselt, Tom Schaul, Georg Ostrovski, Will Dabney, Dan Horgan, Bilal Piot, Mohammad Azar, David Silver

Early discovery. Linked by one identifiable commenter. This paper is outside the main ranking; a mention is not an endorsement.

Abstract

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.

arXiv comments
Under review as a conference paper at AAAI 2018
Journal reference
DOI
Subjects
cs.AIArtificial Intelligence cs.LGMachine Learning

On Hacker News

Linked by 1 identifiable commenter in 1 comment across 1 thread, from Oct 2020 to Oct 2020. Found in 2 HN submissions from Oct 2017 to Aug 2018. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments1 thread

  1. Reinforcement learning is supervised learning on optimized data 1 comment

    • > empirically demonstrate improved goal-reaching performance and robustness over current RL algorithms It's interesting that their choice of current algorithms includes PPO but not e.g. Deepmind's Rainbow agent that achieved state of the art performance on many measures…

      kliptView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.