SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2205.13697 · 2022

FedFormer: Contextual Federation with Attention in Reinforcement Learning

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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, 0 violated it and 1 has no contract verdict; 1 failure of our instrument; 0 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/2205.13697.json · badge: /api/ran/2205.13697.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
liamhebert/FedFormer canonical (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
FunctionStatusWhere it lives
create_stats_ordered_dict Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
liamhebert/FedFormer/rlkit/core/eval_util.py
pointer only (licence: MIT); the stored copy get_code serves, from aviralkumar2907/CQL, is pointer only (licence: NONE) · get_code("fadf5f762ff04cd6")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from aviralkumar2907/CQL, 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.

get_average_returns Ran
ran, honoured the contract we drafted
liamhebert/FedFormer/rlkit/core/eval_util.py
pointer only (licence: MIT); the stored copy get_code serves, from aviralkumar2907/CQL, is pointer only (licence: NONE) · get_code("a5d10a0b704c8db7")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from aviralkumar2907/CQL, 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.

make_optimizer Ran
ran on a synthesized input
liamhebert/FedFormer/garage/_functions.py
code served (permissive licence) · get_code("8a3741971be6face")
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 Adam. 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
import torch.optim as optim

torch.manual_seed(0)

# Create a simple PyTorch module
class SimpleModule(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

module = SimpleModule()

# Test case 1: optimizer_type as a type with module and kwargs
ARGS = {
    "optimizer_type": optim.Adam,
    "module": module,
    "lr": 0.001,
    "betas": (0.9, 0.999),
    "eps": 1e-8,
    "weight_decay": 0.0,
}
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 Adam — a Adam output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Adam 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

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 3 later) and 0 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
get_average_returns 24 other papers
9 dated earlier, 15 later
1903.08254 (2019-03)
Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables
1910.11670 (2019-10)
Contextual Imagined Goals for Self-Supervised Robotic Learning
1912.11032 (2019-12)
Towards Practical Multi-Object Manipulation using Relational Reinforcement Learning
and 21 more not named here
create_stats_ordered_dict 18 other papers
6 dated earlier, 12 later
1910.11670 (2019-10)
Contextual Imagined Goals for Self-Supervised Robotic Learning
2006.04779 (2020-06)
Conservative Q-Learning for Offline Reinforcement Learning
2006.13916 (2020-06)
Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers
and 15 more not named here
make_optimizer 2 other papers
1 dated earlier, 1 later
1604.06778 (2016-04)
Benchmarking Deep Reinforcement Learning for Continuous Control
2206.06614 (2022-06)
Transformers are Meta-Reinforcement Learners

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 core issue in multi-agent federated reinforcement learning is defining how to aggregate insights from multiple agents. This is commonly done by taking the average of each participating agent's model weights into one common model (FedAvg). We instead propose FedFormer, a novel federation strategy that utilizes Transformer Attention to contextually aggregate embeddings from models originating from different learner agents. In so doing, we attentively weigh the contributions of other agents with respect to the current agent's environment and learned relationships, thus providing a more effective and efficient federation. We evaluate our methods on the Meta-World environment and find that our approach yields significant improvements over FedAvg and non-federated Soft Actor-Critic single-agent methods. Our results compared to Soft Actor-Critic show that FedFormer achieves higher episodic return while still abiding by the privacy constraints of federated learning. Finally, we also demonstrate improvements in effectiveness with increased agent pools across all methods in certain tasks. This is contrasted by FedAvg, which fails to make noticeable improvements when scaled.

For agents

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

get_harvested_code_for_paper("2205.13697")
get_code_for_paper("2205.13697")
have("2205.13697")

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

curl https://syntology.ai/api/ran/2205.13697.json

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

[![Syntology run record](https://syntology.ai/api/ran/2205.13697.svg)](https://syntology.ai/paper/2205.13697)

Connect an agent — have() is free.