Papers › Adaptive Rational Activations to Boost Deep Reinforcement Learning
Adaptive Rational Activations to Boost Deep Reinforcement Learning
Quentin Delfosse, Patrick Schramowski, Martin Mundt, Alejandro Molina, Kristian Kersting
Latest insights from biology show that intelligence not only emerges from the connections between neurons but that individual neurons shoulder more computational responsibility than previously anticipated. This perspective should be critical in the context of constantly changing distinct reinforcement learning environments, yet current approaches still primarily employ static activation functions. In this work, we motivate why rationals are suitable for adaptable activation functions and why their inclusion into neural networks is crucial. Inspired by recurrence in residual networks, we derive a condition under which rational units are closed under residual connections and formulate a naturally regularised version: the recurrent-rational. We demonstrate that equipping popular algorithms with (recurrent-)rational activations leads to consistent improvements on Atari games, especially turning simple DQN into a solid approach, competitive to DDQN and Rainbow.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="2102.09407")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2102.09407", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2102.09407")
Code
Syntology 6 code samples harvested from 2 repositories linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 6 where the contract check could not run; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.
By repository: official repository: 6 samples from 2 repositories, 6 ran (0 with no instrument failure; 6 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.
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
6 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
Licence: 3 of the 6 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 3 samples whose link to this paper records no repository are listed under one of this paper's own repositories, because identical code was harvested from it for another paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.
Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.
Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.
39ec3d1f9d97cc5c · report
fixture: signature x:Tensor/2/float, weight_numerator:Tensor/1/float, weight_denominator:Tensor/1/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-22 15a510212432a6c3 · report
fixture: signature x:Tensor/2/float, weight_numerator:Tensor/1/float, weight_denominator:Tensor/1/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-22 6e3e9a40d8b5f9f7 · report
fixture: signature x:Tensor/2/float, weight_numerator:Tensor/1/float, weight_denominator:Tensor/1/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-22 6e9f17d4218ef85b · report
fixture: signature x:Tensor/2/float, weight_numerator:Tensor/1/float, weight_denominator:Tensor/1/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-22 b2ce1b13b9074606 · report
fixture: signature x:Tensor/2/float, weight_numerator:Tensor/1/float, weight_denominator:Tensor/1/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-22 960dbf127ba74109 · report
fixture: signature x:Tensor/2/float, weight_numerator:Tensor/1/float, weight_denominator:Tensor/1/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-22 Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Atari Games | Atari 2600 Asterix | Rational DQN Average | Score | 18109 | #30 of 49 | Archive leaderboard | report |
| Atari Games | Atari 2600 Asterix | Recurrent Rational DQN Average | Score | 12621 | #37 of 49 | Archive leaderboard | report |
| Atari Games | Atari 2600 Battle Zone | Recurrent Rational DQN Average | Score | 25749 | #30 of 47 | Archive leaderboard | report |
| Atari Games | Atari 2600 Battle Zone | Rational DQN Average | Score | 23403 | #35 of 47 | Archive leaderboard | report |
| Atari Games | Atari 2600 Breakout | Recurrent Rational DQN Average | Score | 336 | #40 of 58 | Archive leaderboard | report |
| Atari Games | Atari 2600 Breakout | Rational DQN Average | Score | 316 | #41 of 58 | Archive leaderboard | report |
| Atari Games | Atari 2600 Enduro | Rational DQN Average | Score | 1043 | #30 of 48 | Archive leaderboard | report |
| Atari Games | Atari 2600 Enduro | Recurrent Rational DQN Average | Score | 957 | #31 of 48 | Archive leaderboard | report |
| Atari Games | Atari 2600 James Bond | Recurrent Rational DQN Average | Score | 1137 | #22 of 45 | Archive leaderboard | report |
| Atari Games | Atari 2600 James Bond | Rational DQN Average | Score | 1122 | #23 of 45 | Archive leaderboard | report |
| Atari Games | Atari 2600 Kangaroo | Recurrent Rational DQN Average | Score | 5266 | #28 of 47 | Archive leaderboard | report |
| Atari Games | Atari 2600 Kangaroo | Rational DQN Average | Score | 2941 | #31 of 47 | Archive leaderboard | report |
| Atari Games | Atari 2600 Pong | Recurrent Rational DQN Average | Score | 18.13 | #40 of 52 | Archive leaderboard | report |
| Atari Games | Atari 2600 Pong | Rational DQN Average | Score | 18.04 | #41 of 52 | Archive leaderboard | report |
| Atari Games | Atari 2600 Q*Bert | Rational DQN Average | Score | 14436 | #30 of 57 | Archive leaderboard | report |
| Atari Games | Atari 2600 Q*Bert | Recurrent Rational DQN Average | Score | 14080 | #34 of 57 | Archive leaderboard | report |
| Atari Games | Atari 2600 Seaquest | Recurrent Rational DQN Average | Score | 7460 | #27 of 57 | Archive leaderboard | report |
| Atari Games | Atari 2600 Seaquest | Rational DQN Average | Score | 6603 | #29 of 57 | Archive leaderboard | report |
| Atari Games | Atari 2600 Skiing | Recurrent Rational DQN Average | Score | -23582 | #16 of 23 | Archive leaderboard | report |
| Atari Games | Atari 2600 Skiing | Rational DQN Average | Score | -23487 | #17 of 23 | Archive leaderboard | report |
| Atari Games | Atari 2600 Space Invaders | Recurrent Rational DQN Average | Score | 1395 | #40 of 55 | Archive leaderboard | report |
| Atari Games | Atari 2600 Space Invaders | Rational DQN Average | Score | 650 | #51 of 55 | Archive leaderboard | report |
| Atari Games | Atari 2600 Tennis | Recurrent Rational DQN Average | Score | 20.6 | #10 of 43 | Archive leaderboard | report |
| Atari Games | Atari 2600 Tennis | Rational DQN Average | Score | 20.5 | #11 of 43 | Archive leaderboard | report |
| Atari Games | Atari 2600 Time Pilot | Rational DQN Average | Score | 17632 | #13 of 44 | Archive leaderboard | report |
| Atari Games | Atari 2600 Time Pilot | Recurrent Rational DQN Average | Score | 13261 | #15 of 44 | Archive leaderboard | report |
| Atari Games | Atari 2600 Tutankham | Recurrent Rational DQN Average | Score | 184 | #27 of 44 | Archive leaderboard | report |
| Atari Games | Atari 2600 Tutankham | Rational DQN Average | Score | 179 | #29 of 44 | Archive leaderboard | report |
| Atari Games | Atari 2600 Video Pinball | Rational DQN Average | Score | 149712 | #30 of 42 | Archive leaderboard | report |
| Atari Games | Atari 2600 Video Pinball | Recurrent Rational DQN Average | Score | 86942 | #34 of 42 | 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.
Methods
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