SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2101.04237 · AAAI · 2021

Solving Common-Payoff Games with Approximate Policy Iteration

Samuel Sokota, Marc Lanctot, Michael Bowling, Elnaz Davoodi, Edward Lockhart, Finbarr Timbers, Ryan Orazio, Neil Burch, Martin Schmid

arXiv · PDF · Open in the Atlas

Code that ran

2 of 9 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 failures of our instrument; 7 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/2101.04237.json · badge: /api/ran/2101.04237.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
ssokota/capi marked official in Papers with Code
Papers with Code archive
2 ran · 7 no recorded run
FunctionStatusWhere it lives
NN Ran
ran on a synthesized input · constructed an object; no result was computed
ssokota/capi/capi/agents.py
code served (permissive licence) · get_code("4d846c442d1f74cd")
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, NN: 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)

# Parameters for NN constructor
input_size = 12  # 2 * num_items + 2 * num_utterances = 2*3 + 2*3 = 12
hidden_size = 8
num_items = 3
num_utterances = 3

ARGS = {
    'input_size': input_size,
    'hidden_size': hidden_size,
    'num_items': num_items,
    'num_utterances': num_utterances
}
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 NN — 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 NN 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
State Ran
ran on a synthesized input · constructed an object; no result was computed
ssokota/capi/capi/agents.py
code served (permissive licence) · get_code("6a41dfa5b1829b26")
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, State: 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 os

torch.manual_seed(0)

# Construct a valid joint probability distribution
# Shape: [num_items, num_items] = [4, 4]
# Must be a valid joint probability distribution (sums to 1 over last two dims)
dist = torch.tensor([
    [0.1, 0.05, 0.05, 0.05],
    [0.05, 0.1, 0.05, 0.05],
    [0.05, 0.05, 0.1, 0.05],
    [0.05, 0.05, 0.05, 0.1]
], dtype=torch.float32)

# Normalize to ensure it sums to 1
dist = dist / dist.sum()

num_items = 4
num_utterances = 3

spub = []

ARGS = {
    'dist': dist,
    'num_utterances': num_utterances,
    'spub': spub,
}
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 State — 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 State 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
Agent Not yet run
unverified (harvested, no recorded run)
ssokota/capi/capi/agents.py
code served (permissive licence) · get_code("f75ce66758a1ed20")
How it ran

no invocation recorded.

assert_element Not yet run
unverified (harvested, no recorded run)
ssokota/capi/capi/agents.py
code served (permissive licence) · get_code("f64a58fc81c08af4")
How it ran

no invocation recorded.

assert_joint_probability Not yet run
unverified (harvested, no recorded run)
ssokota/capi/capi/agents.py
code served (permissive licence) · get_code("625d6e259bb25eed")
How it ran

no invocation recorded.

assert_label_prescription Not yet run
unverified (harvested, no recorded run)
ssokota/capi/capi/agents.py
code served (permissive licence) · get_code("bfb9f5a5d8c5237f")
How it ran

no invocation recorded.

assert_num_dims Not yet run
unverified (harvested, no recorded run)
ssokota/capi/capi/agents.py
code served (permissive licence) · get_code("1f06f9d6110f4d9e")
How it ran

no invocation recorded.

assert_prescription Not yet run
unverified (harvested, no recorded run)
ssokota/capi/capi/agents.py
code served (permissive licence) · get_code("8aedc01b97e4426d")
How it ran

no invocation recorded.

assert_shape Not yet run
unverified (harvested, no recorded run)
ssokota/capi/capi/agents.py
code served (permissive licence) · get_code("6ed2f3f73ed808fe")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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 9 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

For artificially intelligent learning systems to have widespread applicability in real-world settings, it is important that they be able to operate decentrally. Unfortunately, decentralized control is difficult-computing even an epsilon-optimal joint policy is a NEXP complete problem. Nevertheless, a recently rediscovered insight-that a team of agents can coordinate via common knowledge-has given rise to algorithms capable of finding optimal joint policies in small common-payoff games. The Bayesian action decoder (BAD) leverages this insight and deep reinforcement learning to scale to games as large as two-player Hanabi. However, the approximations it uses to do so prevent it from discovering optimal joint policies even in games small enough to brute force optimal solutions. This work proposes CAPI, a novel algorithm which, like BAD, combines common knowledge with deep reinforcement learning. However, unlike BAD, CAPI prioritizes the propensity to discover optimal joint policies over scalability. While this choice precludes CAPI from scaling to games as large as Hanabi, empirical results demonstrate that, on the games to which CAPI does scale, it is capable of discovering optimal joint policies even when other modern multi-agent reinforcement learning algorithms are unable to do so.

For agents

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

get_harvested_code_for_paper("2101.04237")
get_code_for_paper("2101.04237")
have("2101.04237")

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

curl https://syntology.ai/api/ran/2101.04237.json

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

[![Syntology run record](https://syntology.ai/api/ran/2101.04237.svg)](https://syntology.ai/paper/2101.04237)

Connect an agent — have() is free.