AI Chat AI Image Generator AI Video Text to Speech

Shorter and faster than Sort3AlphaDev

07/23/2023

∙

by Cassio Neri, et al.

∙

∙

Arising from: Mankowitz, D.J., Michi, A., Zhernov, A. et al. Faster sorting algorithms discovered using deep reinforcement learning.Nature 618, 257-263 (2023). doi.org/10.1038/s41586-023-06004-9. The article cited above presents new implementations of sorting algorithms found through deep reinforcement learning that work on a small number of numeric inputs. For 3 numbers, the published implementation contains 17 assembly instructions, and the authors state that no shorter program exists. This note presents two counterexamples for this claim and a straightforward C/C++ implementation that is faster than theirs.

page 2

page 4

research

∙ 03/08/2018

A Multi-Objective Deep Reinforcement Learning Framework

This paper presents a new multi-objective deep reinforcement learning (M...

0 Thanh Thi Nguyen, et al. ∙

research

∙ 11/05/2016

Learning to Play in a Day: Faster Deep Reinforcement Learning by Optimality Tightening

We propose a novel training algorithm for reinforcement learning which c...

0 Frank S. He, et al. ∙

research

∙ 04/03/2009

Time Hopping technique for faster reinforcement learning in simulations

This preprint has been withdrawn by the author for revision...

0 Petar Kormushev, et al. ∙

research

∙ 05/25/2021

Interpretable UAV Collision Avoidance using Deep Reinforcement Learning

The significant components of any successful autonomous flight system ar...

0 Deepak-George Thomas, et al. ∙

research

∙ 02/16/2020

Investigating Simple Object Representations in Model-Free Deep Reinforcement Learning

We explore the benefits of augmenting state-of-the-art model-free deep r...

0 Guy Davidson, et al. ∙

research

∙ 01/24/2018

Psychlab: A Psychology Laboratory for Deep Reinforcement Learning Agents

Psychlab is a simulated psychology laboratory inside the first-person 3D...

0 Joel Z. Leibo, et al. ∙

research

∙ 12/15/2018

On Improving Decentralized Hysteretic Deep Reinforcement Learning

Recent successes of value-based multi-agent deep reinforcement learning ...

0 Xueguang Lu, et al. ∙