SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2212.08235 · NeurIPS · 2022

A Simple Decentralized Cross-Entropy Method

Dale Schuurmans, Jun Luo, Zichen Zhang, Jun Jin, Martin Jagersand

arXiv · PDF · Open in the Atlas

Code that ran

1 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 3 no recorded run), measured 2026-11-22; 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/2212.08235.json · badge: /api/ran/2212.08235.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
vincentzhang/decentcem canonical (classifier label)
classifier basis: classifier_2025
1 ran · 3 no recorded run
FunctionStatusWhere it lives
Optimizer Ran
ran on a synthesized input · constructed an object; no result was computed
vincentzhang/decentcem/dmbrl/misc/optimizers/decent_cem.py
code served (permissive licence) · get_code("b2643bc67ba7017b")
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, Optimizer: 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 numpy as np
import torch
import torch.nn as nn

torch.manual_seed(0)

# Since Optimizer is a base class with abstract methods, we need to create
# a concrete subclass to instantiate it for testing purposes
class ConcreteOptimizer:
    def __init__(self, *args, **kwargs):
        self.sy_cur_obs = None
        self._proposed_act_seqs_ph = None

    def setup(self, cost_function, tf_compatible):
        pass

    def save(self, *args, **kwargs):
        pass

    def reset(self):
        pass

    def obtain_solution(self, *args, **kwargs):
        return np.zeros((5, 4))

    def get_policy_network(self):
        return None

    def train_policy_network(self):
        return False

    def set_tf_writer(self, tf_write):
        pass

    def set_sy_cur_obs(self, sy_cur_obs):
        self.sy_cur_obs = sy_cur_obs

    def forward_policy_propose(self, predict_next_obs, sy_cur_obs):
        pass

    def reset_prev_sol(self, prev_sol):
        return prev_sol

    def update_prev_sol(self, per, dU, soln):
        prev_sol = np.concatenate([np.copy(soln)[per * dU:], np.zeros(per * dU)])
        return prev_sol


# Create a simple cost function
def simple_cost_function(x):
    return np.sum(x ** 2)


ARGS = {}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Optimizer — 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 Optimizer 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
CEMOptimizer Not yet run
unverified (harvested, no recorded run)
vincentzhang/decentcem/dmbrl/misc/optimizers/decent_cem.py
code served (permissive licence) · get_code("24f8caf9c5ab0b4a")
How it ran

no invocation recorded.

DecentCEMOptimizer Not yet run
unverified (harvested, no recorded run)
vincentzhang/decentcem/dmbrl/misc/optimizers/decent_cem.py
code served (permissive licence) · get_code("8010e46e36def6c8")
How it ran

no invocation recorded.

plot_1d1 Not yet run
unverified (harvested, no recorded run)
vincentzhang/decentcem/utils/plotter.py
code served (permissive licence) · get_code("c720ef21f3a8d841")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 4 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 2026-11-22.

Repositories linked to this paper

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

Abstract

Cross-Entropy Method (CEM) is commonly used for planning in model-based reinforcement learning (MBRL) where a centralized approach is typically utilized to update the sampling distribution based on only the top-k operation's results on samples. In this paper, we show that such a centralized approach makes CEM vulnerable to local optima, thus impairing its sample efficiency. To tackle this issue, we propose Decentralized CEM (DecentCEM), a simple but effective improvement over classical CEM, by using an ensemble of CEM instances running independently from one another, and each performing a local improvement of its own sampling distribution. We provide both theoretical and empirical analysis to demonstrate the effectiveness of this simple decentralized approach. We empirically show that, compared to the classical centralized approach using either a single or even a mixture of Gaussian distributions, our DecentCEM finds the global optimum much more consistently thus improves the sample efficiency. Furthermore, we plug in our DecentCEM in the planning problem of MBRL, and evaluate our approach in several continuous control environments, with comparison to the stateof-art CEM based MBRL approaches (PETS and POPLIN). Results show sample efficiency improvement by simply replacing the classical CEM module with our DecentCEM module, while only sacrificing a reasonable amount of computational cost. Lastly, we conduct ablation studies for more in-depth analysis. Code is available at https://github.com/vincentzhang/decentCEM.

For agents

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

get_harvested_code_for_paper("2212.08235")
get_code_for_paper("2212.08235")
have("2212.08235")

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

curl https://syntology.ai/api/ran/2212.08235.json

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

[![Syntology run record](https://syntology.ai/api/ran/2212.08235.svg)](https://syntology.ai/paper/2212.08235)

Connect an agent — have() is free.