Papers › Temporal-Difference Learning Using Distributed Error Signals

Temporal-Difference Learning Using Distributed Error Signals

6 Nov 2024arXiv:2411.03604archive 2025-07-28

Jonas Guan, Shon Eduard Verch, Claas Voelcker, Ethan C. Jackson, Nicolas Papernot, William A. Cunningham

A computational problem in biological reward-based learning is how credit assignment is performed in the nucleus accumbens (NAc). Much research suggests that NAc dopamine encodes temporal-difference (TD) errors for learning value predictions. However, dopamine is synchronously distributed in regionally homogeneous concentrations, which does not support explicit credit assignment (like used by backpropagation). It is unclear whether distributed errors alone are sufficient for synapses to make coordinated updates to learn complex, nonlinear reward-based learning tasks. We design a new deep Q-learning algorithm, Artificial Dopamine, to computationally demonstrate that synchronously distributed, per-layer TD errors may be sufficient to learn surprisingly complex RL tasks. We empirically evaluate our algorithm on MinAtar, the DeepMind Control Suite, and classic control tasks, and show it often achieves comparable performance to deep RL algorithms that use backpropagation.

PaperPDFCodeCode Syntology ran

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):

Code

Syntology 24 code samples harvested from 2 repositories linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 14 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 3 samples from 1 repository, 2 ran (2 with no instrument failure; 0 where Syntology's instrument failed); found in paper text by Syntology: 21 samples from 1 repository, 8 ran (4 with no instrument failure; 4 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.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

social-ai-uoft/ad-paper officialmentioned on GitHubjaxMITSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

24 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 14 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
4ran · our draft was wrong
4ran
14unverified

Licence: 1 of the 24 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. 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. “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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

social-ai-uoft/ad-paper official repository 3 samples, 2 ran (0 instrument-failed) · 1 unverified
huber in 13 papers src/artificial_dopamine/algorithms/ad_qrdqn.py ran · violated contract fingerprinted MIT (permissive) · 32ccda7b7e95f774 · report fixture: signature td:ArrayImpl/1/float · returned ArrayImpl · level recorded 2026-09-25
k_folding src/artificial_dopamine/ad_layers.py ran MIT (permissive) · 89936e0c6682decc · report fixture: signature x:ArrayImpl/2/float, p0:ArrayImpl/2/float, k:int/0/int, pad:bool/0/bool · returned ArrayImpl · level recorded 2026-09-25
get_quantile_at_action src/artificial_dopamine/algorithms/ad_qrdqn.py unverified MIT (permissive) · e16eeb112aeeb02b · report
google/jax found in paper text by Syntology 21 samples, 8 ran (4 instrument-failed) · 13 unverified
add_abstract jax/_src/ad_util.py ran · our draft was wrong Apache-2.0 (permissive) · 2084aa5b3266ab8f · report fixture: signature x:ShapedArray/2/float, y:ShapedArray/2/float · returned ShapedArray · level recorded 2026-09-24
blocked_fold_in jax/_src/blocked_sampler.py ran Apache-2.0 (permissive) · cac8281b61c863de · report fixture: signature global_key:ArrayImpl/1/int, total_size:tuple/1/int, block_size:tuple/1/int, tile_size:tuple/1/int, block_index:tuple/1/ArrayImpl · returned list · level recorded 2026-09-24
buffer_callback jax/_src/buffer_callback.py ran · our draft was wrong Apache-2.0 (permissive) · 29226c63dfc413f0 · report fixture: signature callback:callable/0/?, result_shape_dtypes:ShapeDtypeStruct/1/int, has_side_effect:bool/0/bool, vmap_method:NoneType/0/?, input_output_aliases:NoneType/0/?, command_buffer_compatible:bool/0/bool · returned function · level recorded 2026-09-24
dots_saveable jax/_src/ad_checkpoint.py ran Apache-2.0 (permissive) · 8b0add7ca6f2c489 · report fixture: signature prim:Primitive/0/? · returned bool · level recorded 2026-09-24
identity in 174 papers
census: 11 implementations from 39 papers, 3 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
jax/_src/ad_checkpoint.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 9910e2fc297f8665 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
offload_dot_with_no_batch_dims jax/_src/ad_checkpoint.py ran · our draft was wrong Apache-2.0 (permissive) · 810b7a396afb59d3 · report fixture: signature offload_src:str/0/str, offload_dst:str/0/str · returned OffloadDotWithNoBatchDims · level recorded 2026-09-24
sample_block jax/_src/blocked_sampler.py ran Apache-2.0 (permissive) · 90d492383f675799 · report fixture: signature sampler_fn:callable/0/?, keys:list/1/list, block_size:tuple/1/int, tile_size:tuple/1/int · returned ArrayImpl · level recorded 2026-09-24
save_from_both_policies jax/_src/ad_checkpoint.py ran · our draft was wrong Apache-2.0 (permissive) · 2e107afaca8a349d · report fixture: signature policy_1:callable/0/?, policy_2:callable/0/? · returned function · level recorded 2026-09-24
add_impl jax/_src/ad_util.py unverified Apache-2.0 (permissive) · 7dc8234c8244b402 · report
add_jaxvals jax/_src/ad_util.py unverified Apache-2.0 (permissive) · c4008ce797ce88b7 · report
argnums_partial jax/_src/api_util.py unverified Apache-2.0 (permissive) · 0e74585505a2eea7 · report
dots_with_no_batch_dims_saveable jax/_src/ad_checkpoint.py unverified Apache-2.0 (permissive) · 23b150f55677eecf · report
flatten_fun jax/_src/api_util.py unverified Apache-2.0 (permissive) · eb71d064139c0c1e · report
flatten_fun_nokwargs jax/_src/api_util.py unverified Apache-2.0 (permissive) · 3ccc19e76d1ee880 · report
get in 42 papers jax/_src/cache_key.py unverified Apache-2.0 (permissive) · 9fc0e9452ec7806b · report
io_callback_batching_rule jax/_src/callback.py unverified Apache-2.0 (permissive) · a3183105bcb38a23 · report
jit jax/_src/api.py unverified Apache-2.0 (permissive) · 1dc34cecff86ce05 · report
jit jax/_src/api.py unverified Apache-2.0 (permissive) · e0971622bbe8538e · report
pure_callback jax/_src/callback.py unverified Apache-2.0 (permissive) · a860c143f6dbe657 · report
pure_callback jax/_src/callback.py unverified Apache-2.0 (permissive) · 21ed500dc8476b88 · report
pure_callback_lowering jax/_src/callback.py unverified Apache-2.0 (permissive) · 55ac98a7c46161c0 · report

Tasks

Q-Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Q-Learning

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