Papers › Optimizing the Neural Architecture of Reinforcement Learning Agents

Optimizing the Neural Architecture of Reinforcement Learning Agents

30 Nov 2020arXiv:2011.14632archive 2025-07-28

N. Mazyavkina, S. Moustafa, I. Trofimov, E. Burnaev

Reinforcement learning (RL) enjoyed significant progress over the last years. One of the most important steps forward was the wide application of neural networks. However, architectures of these neural networks are typically constructed manually. In this work, we study recently proposed neural architecture search (NAS) methods for optimizing the architecture of RL agents. We carry out experiments on the Atari benchmark and conclude that modern NAS methods find architectures of RL agents outperforming a manually selected one.

Paper PDF Code

Code

NinaMaz/NAS_RL_torch officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Atari Games Meta Reinforcement Learning Neural Architecture Search Reinforcement Learning Reinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Atari Games	Atari 2600 Breakout	SPOS	Score	180.6	#47 of 58	Archive leaderboard	report
Atari Games	Atari 2600 Breakout	ENAS Search space 1	Score	161.1	#48 of 58	Archive leaderboard	report
Atari Games	Atari 2600 Breakout	SPOS Search space 1	Score	144.4	#49 of 58	Archive leaderboard	report
Atari Games	Atari 2600 Breakout	ENAS	Score	91.4	#50 of 58	Archive leaderboard	report
Atari Games	Atari 2600 Freeway	ENAS	Score	22	#45 of 59	Archive leaderboard	report
Atari Games	Atari 2600 Freeway	SPOS	Score	22	#46 of 59	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections