SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2411.03604 · NeurIPS · 2024

Temporal-Difference Learning Using Distributed Error Signals

Nicolas Papernot, Jonas Guan, Shon Verch, Claas Voelcker, Ethan Jackson, William Cunningham

arXiv · PDF · Open in the Atlas

Code that ran

10 of 24 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 1 violated it and 1 has no contract verdict; 7 failures of our instrument; 14 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2411.03604.json · badge: /api/ran/2411.03604.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
google/jax canonical (classifier label)
classifier basis: plan_row
8 ran · 13 no recorded run
social-ai-uoft/ad-paper canonical (classifier label)
classifier basis: census
2 ran · 1 no recorded run
FunctionStatusWhere it lives
add_abstract Ran
ran; our contract draft was wrong, not the code
google/jax/jax/_src/ad_util.py
code served (permissive licence) · get_code("2084aa5b3266ab8f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ShapedArray. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import jax
import jax.numpy as jnp
from jax._src import core
from jax._src.core import Primitive

# Create the primitive
add_jaxvals_p = Primitive('add_any')

@add_jaxvals_p.def_abstract_eval
def add_abstract(x, y):
    assert core.typematch(x, y), (x, y)
    return x

# Construct valid arguments for add_abstract
# The function takes two JAX abstract values that must match in type
# We'll use JAX's abstract values

# Create abstract values - these represent the shape/dtype info of JAX arrays
x_abstract = core.ShapedArray(shape=(2, 4), dtype=jnp.float32)
y_abstract = core.ShapedArray(shape=(2, 4), dtype=jnp.float32)

ARGS = {
    'x': x_abstract,
    'y': y_abstract,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
jax — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ShapedArray — a ShapedArray output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ShapedArray output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
blocked_fold_in Ran
ran; our contract draft was wrong, not the code
google/jax/jax/_src/blocked_sampler.py
code served (permissive licence) · get_code("cac8281b61c863de")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 3, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import jax
import jax.numpy as jnp

# Set seed for reproducibility
jax.config.update("jax_default_prng_impl", "threefry2x32")

# Create a global PRNGKey
global_key = jax.random.PRNGKey(0)

# Define the arguments for blocked_fold_in
# total_size: shape of the array being generated (16x512)
total_size = (16, 512)

# block_size: shape of an individual block (16x128)
block_size = (16, 128)

# tile_size: smallest unit at which samples are generated (8x128)
tile_size = (8, 128)

# block_index: which block to generate keys for - 2D indices
# Using jnp arrays as ArrayLike objects
block_index = (jnp.array(0), jnp.array(0))

ARGS = {
    "global_key": global_key,
    "total_size": total_size,
    "block_size": block_size,
    "tile_size": tile_size,
    "block_index": block_index,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
jax — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 3, dtype family int — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
buffer_callback Ran
ran; our contract draft was wrong, not the code
google/jax/jax/_src/buffer_callback.py
code served (permissive licence) · get_code("29226c63dfc413f0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned function. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import jax
import jax.numpy as jnp
from jax._src import core
from jax._src import tree_util


def simple_callback(ctx, out, x):
    """A simple callback that adds 1 to the input."""
    np.asarray(out)[...] = np.asarray(x) + 1


# Create a small input array
x = jnp.array([1, 2, 3, 4], dtype=jnp.int32)

# Define the output shape and dtype
result_shape_dtypes = jax.ShapeDtypeStruct(shape=(4,), dtype=jnp.int32)

ARGS = {
    'callback': simple_callback,
    'result_shape_dtypes': result_shape_dtypes,
    'has_side_effect': False,
    'vmap_method': None,
    'input_output_aliases': None,
    'command_buffer_compatible': False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
jax, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
dots_saveable Ran
ran on a synthesized input
google/jax/jax/_src/ad_checkpoint.py
code served (permissive licence) · get_code("8b0add7ca6f2c489")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned bool, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
from jax._src.lax import lax as lax_internal
from jax._src.lax import convolution as lax_convolution

torch.manual_seed(0)

# Create a mock primitive object that has a name attribute
class MockPrimitive:
    def __init__(self, name=None):
        self.name = name

# Test with dot_general_p
prim_dot = lax_internal.dot_general_p

# Test with conv_general_dilated_p
prim_conv = lax_convolution.conv_general_dilated_p

# Test with a custom primitive with 'scaled_matmul_wrapper' name
prim_custom = MockPrimitive(name='scaled_matmul_wrapper')

# Test with a primitive that doesn't match any condition
prim_other = MockPrimitive(name='other_op')

# The function takes prim as first argument, *_ captures any additional positional args,
# and **__ captures any keyword arguments. We need to call it with just a primitive.

ARGS = {
    'prim': prim_dot,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
jax, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
huber Ran
ran, violated the contract we drafted
social-ai-uoft/ad-paper/src/artificial_dopamine/algorithms/ad_qrdqn.py
code served (permissive licence) · get_code("32ccda7b7e95f774")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ArrayImpl, ndim 1, dtype family float, shape (4,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import jax
import jax.numpy as jnp

# Create a small temporal difference error array
# The function expects a jnp.ndarray and applies Huber loss element-wise
td_error = jnp.array([0.5, 1.5, -0.3, 2.0])

ARGS = {
    "td": td_error,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
jax — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ArrayImpl, ndim 1, dtype family float, shape (4,) — shape (4,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
identity Ran
ran, honoured the contract we drafted
google/jax/jax/_src/ad_checkpoint.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from dholzmueller/universal_double_descent, is pointer only (licence: NONE) · get_code("9910e2fc297f8665")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from dholzmueller/universal_double_descent, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

k_folding Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
social-ai-uoft/ad-paper/src/artificial_dopamine/ad_layers.py
code served (permissive licence) · get_code("89936e0c6682decc")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ArrayImpl, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import jax
import jax.numpy as jnp

# Create small test arrays for k_folding
# x: shape (N, H_in) where H_in is divisible by k
# p0: shape (N, H_in/k) where H_in/k is the chunk size

# Example: batch_size=2, H_in=8, k=4, so chunk_size=2
x = jax.random.normal(jax.random.PRNGKey(0), (2, 8))
p0 = jax.random.normal(jax.random.PRNGKey(1), (2, 2))
k = 4
pad = True

ARGS = {
    'x': x,
    'p0': p0,
    'k': k,
    'pad': pad
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
jax — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ArrayImpl, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
offload_dot_with_no_batch_dims Ran
ran; our contract draft was wrong, not the code
google/jax/jax/_src/ad_checkpoint.py
code served (permissive licence) · get_code("810b7a396afb59d3")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned OffloadDotWithNoBatchDims. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np
from jax._src.interpreters import partial_eval as pe
from jax._src.lax import lax as lax_internal

torch.manual_seed(0)

# The function offload_dot_with_no_batch_dims takes two string parameters:
# offload_src and offload_dst. These are used to construct an OffloadDotWithNoBatchDims
# instance, which stores them as attributes and uses them when creating a 
# pe.Offloadable object.

ARGS = {
    "offload_src": "cpu",
    "offload_dst": "gpu"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
jax, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type OffloadDotWithNoBatchDims — a OffloadDotWithNoBatchDims output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a OffloadDotWithNoBatchDims output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
sample_block Ran
ran; our contract draft was wrong, not the code
google/jax/jax/_src/blocked_sampler.py
code served (permissive licence) · get_code("90d492383f675799")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ArrayImpl, ndim 2, dtype family float, shape (4, 6) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import jax
import jax.numpy as jnp
import jax.random as jrandom

# Define a simple sampler function that matches the SampleFn protocol
def mock_sampler_fn(key, shape=None):
    """A mock sampling function that returns random uniform samples."""
    return jrandom.uniform(key, shape=shape)

# Create a random key for the keys parameter
# The keys should be a nested structure/grid of JAX random keys
# For a 2D block, we need a 2D grid of keys
seed = 42
master_key = jrandom.PRNGKey(seed)

# Generate a grid of keys matching the size_in_tiles structure
# If block_size=(4, 6) and tile_size=(2, 3), size_in_tiles=(2, 2)
# So we need a 2x2 grid of keys
keys_2d = []
for i in range(2):
    row = []
    for j in range(2):
        master_key, subkey = jrandom.split(master_key)
        row.append(subkey)
    keys_2d.append(row)

ARGS = {
    "sampler_fn": mock_sampler_fn,
    "keys": keys_2d,
    "block_size": (4, 6),
    "tile_size": (2, 3),
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
jax — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ArrayImpl, ndim 2, dtype family float, shape (4, 6) — shape (4, 6) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
save_from_both_policies Ran
ran; our contract draft was wrong, not the code
google/jax/jax/_src/ad_checkpoint.py
code served (permissive licence) · get_code("2e107afaca8a349d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned function. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

def policy_1(prim, *args, **params):
    """Simple policy that returns True for even primitives."""
    return True

def policy_2(prim, *args, **params):
    """Simple policy that returns False for odd primitives."""
    return False

ARGS = {
    "policy_1": policy_1,
    "policy_2": policy_2,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
add_impl Not yet run
unverified (harvested, no recorded run)
google/jax/jax/_src/ad_util.py
code served (permissive licence) · get_code("7dc8234c8244b402")
How it ran

no invocation recorded.

add_jaxvals Not yet run
unverified (harvested, no recorded run)
google/jax/jax/_src/ad_util.py
code served (permissive licence) · get_code("c4008ce797ce88b7")
How it ran

no invocation recorded.

argnums_partial Not yet run
unverified (harvested, no recorded run)
google/jax/jax/_src/api_util.py
code served (permissive licence) · get_code("0e74585505a2eea7")
How it ran

no invocation recorded.

dots_with_no_batch_dims_saveable Not yet run
unverified (harvested, no recorded run)
google/jax/jax/_src/ad_checkpoint.py
code served (permissive licence) · get_code("23b150f55677eecf")
How it ran

no invocation recorded.

flatten_fun Not yet run
unverified (harvested, no recorded run)
google/jax/jax/_src/api_util.py
code served (permissive licence) · get_code("eb71d064139c0c1e")
How it ran

no invocation recorded.

flatten_fun_nokwargs Not yet run
unverified (harvested, no recorded run)
google/jax/jax/_src/api_util.py
code served (permissive licence) · get_code("3ccc19e76d1ee880")
How it ran

no invocation recorded.

get Not yet run
unverified (harvested, no recorded run)
google/jax/jax/_src/cache_key.py
code served (permissive licence) · get_code("9fc0e9452ec7806b")
How it ran

no invocation recorded.

get_quantile_at_action Not yet run
unverified (harvested, no recorded run)
social-ai-uoft/ad-paper/src/artificial_dopamine/algorithms/ad_qrdqn.py
code served (permissive licence) · get_code("e16eeb112aeeb02b")
How it ran

no invocation recorded.

io_callback_batching_rule Not yet run
unverified (harvested, no recorded run)
google/jax/jax/_src/callback.py
code served (permissive licence) · get_code("a3183105bcb38a23")
How it ran

no invocation recorded.

jit Not yet run
unverified (harvested, no recorded run)
google/jax/jax/_src/api.py
code served (permissive licence) · get_code("1dc34cecff86ce05")
How it ran

no invocation recorded.

jit Not yet run
unverified (harvested, no recorded run)
google/jax/jax/_src/api.py
code served (permissive licence) · get_code("e0971622bbe8538e")
How it ran

no invocation recorded.

pure_callback Not yet run
unverified (harvested, no recorded run)
google/jax/jax/_src/callback.py
code served (permissive licence) · get_code("a860c143f6dbe657")
How it ran

no invocation recorded.

pure_callback Not yet run
unverified (harvested, no recorded run)
google/jax/jax/_src/callback.py
code served (permissive licence) · get_code("21ed500dc8476b88")
How it ran

no invocation recorded.

pure_callback_lowering Not yet run
unverified (harvested, no recorded run)
google/jax/jax/_src/callback.py
code served (permissive licence) · get_code("55ac98a7c46161c0")
How it ran

no invocation recorded.

Also present in other papers' code

Of 24 samples lifted from this paper's linked repositories, 24 carry a function identity and 0 do not. Of the 22 distinct functions with an identity, 17 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 17 later) and 5 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
identity 69 other papers
60 dated earlier, 1 the same month, 8 later · 5 only as an assembly brick
1706.07296 (2017-06)
A Minimal Developmental Model Can Increase Evolvability in Soft Robots
1802.09419 (2018-02)
Stochastic Hyperparameter Optimization through Hypernetworks
1804.06055 (2018-04)
Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation
and 66 more not named here
add_abstract 1 other paper
1 later
2605.26248 (2026-05)
Unified Neural Scaling Laws
add_impl 1 other paper
1 later
2605.26248 (2026-05)
Unified Neural Scaling Laws
add_jaxvals 1 other paper
1 later
2605.26248 (2026-05)
Unified Neural Scaling Laws
argnums_partial 1 other paper
1 later
2605.26248 (2026-05)
Unified Neural Scaling Laws
blocked_fold_in 1 other paper
1 later
2605.26248 (2026-05)
Unified Neural Scaling Laws
buffer_callback 1 other paper
1 later
2605.26248 (2026-05)
Unified Neural Scaling Laws
flatten_fun 1 other paper
1 later
2605.26248 (2026-05)
Unified Neural Scaling Laws
flatten_fun_nokwargs 1 other paper
1 later
2605.26248 (2026-05)
Unified Neural Scaling Laws
get 1 other paper
1 later
2605.26248 (2026-05)
Unified Neural Scaling Laws
io_callback_batching_rule 1 other paper
1 later
2605.26248 (2026-05)
Unified Neural Scaling Laws
jit 1 other paper
1 later
2605.26248 (2026-05)
Unified Neural Scaling Laws
offload_dot_with_no_batch_dims 1 other paper
1 later
2605.26248 (2026-05)
Unified Neural Scaling Laws
pure_callback 1 other paper
1 later
2605.26248 (2026-05)
Unified Neural Scaling Laws
pure_callback_lowering 1 other paper
1 later
2605.26248 (2026-05)
Unified Neural Scaling Laws
sample_block 1 other paper
1 later
2605.26248 (2026-05)
Unified Neural Scaling Laws
save_from_both_policies 1 other paper
1 later
2605.26248 (2026-05)
Unified Neural Scaling Laws

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

A computational problem in biological reward-based learning is how credit assignment is performed in the nucleus accumbens (NAc) to update synaptic weights. 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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2411.03604")
get_code_for_paper("2411.03604")
have("2411.03604")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2411.03604.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2411.03604.svg)](https://syntology.ai/paper/2411.03604)

Connect an agent — have() is free.