SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.06159 · NeurIPS · 2020

Implicit Distributional Reinforcement Learning

Mingyuan Zhou, Yuguang Yue, Zhendong Wang

arXiv · PDF · Open in the Atlas

Code that ran

4 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (4 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-21; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/2007.06159.json · badge: /api/ran/2007.06159.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
zhougroup/IDAC marked official in Papers with Code
Papers with Code archive
4 ran · 1 no recorded run
SeungeonBaek/continuous-agents-test community
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
D_Critic Ran
ran on a synthesized input · constructed an object; no result was computed
zhougroup/IDAC/agents/idac.py
code served (permissive licence) · get_code("16606174c6ce3415")
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 an instance of its own class, D_Critic: the run constructed the object and did not call it, so no result was computed. 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)

# Define dimensions
state_dim = 4
action_dim = 3
noise_dim = 5
device = 'cpu'
layer_norm = True
hidden_sizes = [256, 256]

ARGS = {
    'state_dim': state_dim,
    'action_dim': action_dim,
    'noise_dim': noise_dim,
    'device': device,
    'layer_norm': layer_norm,
    'hidden_sizes': hidden_sizes
}
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 D_Critic — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a D_Critic 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
G_Actor Ran
ran on a synthesized input · constructed an object; no result was computed
zhougroup/IDAC/agents/idac.py
code served (permissive licence) · get_code("d595cdaaa075b310")
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 an instance of its own class, G_Actor: the run constructed the object and did not call it, so no result was computed. 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)

ARGS = {
    "state_dim": 4,
    "action_dim": 3,
    "max_action": 1.0,
    "device": torch.device("cpu"),
    "hidden_sizes": [256, 256],
    "layer_norm": False,
}
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 G_Actor — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a G_Actor 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
Implicit_Actor Ran
ran on a synthesized input · constructed an object; no result was computed
zhougroup/IDAC/agents/idac.py
code served (permissive licence) · get_code("f31bac0ea9e377cf")
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 an instance of its own class, Implicit_Actor: the run constructed the object and did not call it, so no result was computed. 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)

ARGS = {
    "state_dim": 4,
    "action_dim": 3,
    "noise_dim": 2,
    "noise_num": 5,
    "max_action": 1.0,
    "device": "cpu",
    "hidden_sizes": [256, 256],
    "layer_norm": False,
}
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 Implicit_Actor — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Implicit_Actor 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
TanhNormal Ran
ran on a synthesized input · constructed an object; no result was computed
zhougroup/IDAC/agents/idac.py
code served (permissive licence) · get_code("578423b4a2bb1cf9")
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 an instance of its own class, TanhNormal: the run constructed the object and did not call it, so no result was computed. 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
from torch.distributions import Normal

torch.manual_seed(0)

# Create tensors for normal distribution parameters
# Using distinct sizes: batch=2, dim=4
normal_mean = torch.randn(2, 4)
normal_std = torch.abs(torch.randn(2, 4)) + 0.1  # Ensure positive std

device = 'cpu'
epsilon = 1e-06

ARGS = {
    'normal_mean': normal_mean,
    'normal_std': normal_std,
    'device': device,
    'epsilon': epsilon,
}
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 TanhNormal — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a TanhNormal 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
DistCritic Not yet run
unverified (harvested, no recorded run)
SeungeonBaek/continuous-agents-test/agents/IDAC.py
code served (permissive licence) · get_code("2678e0fdb62a4cf9")
How it ran

no invocation recorded.

IDAC Not yet run
unverified (harvested, no recorded run)
zhougroup/IDAC/agents/idac.py
code served (permissive licence) · get_code("3fa2247f371c4678")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 6 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.

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 2026-11-21.

Repositories linked to this paper

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

Abstract

To improve the sample efficiency of policy-gradient based reinforcement learning algorithms, we propose implicit distributional actor-critic (IDAC) that consists of a distributional critic, built on two deep generator networks (DGNs), and a semi-implicit actor (SIA), powered by a flexible policy distribution. We adopt a distributional perspective on the discounted cumulative return and model it with a state-action-dependent implicit distribution, which is approximated by the DGNs that take state-action pairs and random noises as their input. Moreover, we use the SIA to provide a semi-implicit policy distribution, which mixes the policy parameters with a reparameterizable distribution that is not constrained by an analytic density function. In this way, the policy's marginal distribution is implicit, providing the potential to model complex properties such as covariance structure and skewness, but its parameter and entropy can still be estimated. We incorporate these features with an off-policy algorithm framework to solve problems with continuous action space and compare IDAC with state-of-the-art algorithms on representative OpenAI Gym environments. We observe that IDAC outperforms these baselines in most tasks. Python code is provided 1 .

For agents

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

get_harvested_code_for_paper("2007.06159")
get_code_for_paper("2007.06159")
have("2007.06159")

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

curl https://syntology.ai/api/ran/2007.06159.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.06159.svg)](https://syntology.ai/paper/2007.06159)

Connect an agent — have() is free.