Papers › Proximal Learning With Opponent-Learning Awareness

Proximal Learning With Opponent-Learning Awareness

18 Oct 2022arXiv:2210.10125archive 2025-07-28

Stephen Zhao, Chris Lu, Roger Baker Grosse, Jakob Nicolaus Foerster

Learning With Opponent-Learning Awareness (LOLA) (Foerster et al. [2018a]) is a multi-agent reinforcement learning algorithm that typically learns reciprocity-based cooperation in partially competitive environments. However, LOLA often fails to learn such behaviour on more complex policy spaces parameterized by neural networks, partly because the update rule is sensitive to the policy parameterization. This problem is especially pronounced in the opponent modeling setting, where the opponent's policy is unknown and must be inferred from observations; in such settings, LOLA is ill-specified because behaviorally equivalent opponent policies can result in non-equivalent updates. To address this shortcoming, we reinterpret LOLA as approximating a proximal operator, and then derive a new algorithm, proximal LOLA (POLA), which uses the proximal formulation directly. Unlike LOLA, the POLA updates are parameterization invariant, in the sense that when the proximal objective has a unique optimum, behaviorally equivalent policies result in behaviorally equivalent updates. We then present practical approximations to the ideal POLA update, which we evaluate in several partially competitive environments with function approximation and opponent modeling. This empirically demonstrates that POLA achieves reciprocity-based cooperation more reliably than LOLA.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Syntology holds a reference implementation of Proximal Learning With Opponent-Learning Awareness (POLA), generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='Proximal Learning With Opponent-Learning Awareness (POLA)') (how to connect); the free check have('2210.10125') needs no token.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 20 code samples harvested from 2 repositories linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 5 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 13 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 19 samples from 1 repository, 7 ran (5 with no instrument failure; 2 where Syntology's instrument failed); found in paper text by Syntology: 1 sample from 1 repository, 0 ran (0 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 5 of the 7 samples that ran have no recorded date.

silent-zebra/pola officialmentioned in paperjaxMITSyntology: 19 samples, 7 ran (2 instrument-failed) · 12 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

20 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 5 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 13 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

5ran · honoured contract
1ran · our draft was wrong
1ran; the contract check could not run
13unverified

Licence: 0 of the 20 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

silent-zebra/pola official repository 19 samples, 7 ran (2 instrument-failed) · 12 unverified
bin_inttensor_from_int LOLA_exact.py ran · honoured contract MIT (permissive) · 85d7bd3c92bc8523 · report fixture: signature x:int/0/int, n:int/0/int · returned Tensor · level recorded, date not recorded
build_bin_matrix LOLA_exact.py ran · honoured contract fingerprinted MIT (permissive) · d21cebee917ab27f · report fixture: signature n:int/0/int, size:int/0/int · returned Tensor · level recorded, date not recorded
build_p_vector LOLA_exact.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · 321a0e5deba583ee · report fixture: signature n:int/0/int, size:int/0/int, pc:Tensor/1/float, bin_mat:Tensor/2/float · returned Tensor · level recorded, date not recorded
kl_div_jax jax_files/POLA_dice_jax.py ran · honoured contract fingerprinted MIT (permissive) · 70a992b1af899b2d · report fixture: signature curr:ArrayImpl/2/float, target:ArrayImpl/2/float · returned ArrayImpl · level recorded 2026-09-22
magic_box in 7 papers jax_files/POLA_dice_jax.py ran · honoured contract fingerprinted MIT (permissive) · f4166f1f2230b2e7 · report fixture: signature x:ArrayImpl/2/float · returned ArrayImpl · level recorded, date not recorded
rev_kl_div_jax jax_files/POLA_dice_jax.py ran · honoured contract fingerprinted MIT (permissive) · 54e852578016625d · report fixture: signature curr:ArrayImpl/2/float, target:ArrayImpl/2/float · returned ArrayImpl · level recorded 2026-09-22
reverse_cumsum jax_files/POLA_dice_jax.py ran · our draft was wrong fingerprinted MIT (permissive) · 61e0eb0133131d4c · report fixture: signature x:ArrayImpl/2/float, axis:int/0/int · returned ArrayImpl · level recorded, date not recorded
act in 30 papers jax_files/POLA_dice_jax.py unverified MIT (permissive) · 80d4ccc33bef2e8a · report
act_w_iter_over_obs jax_files/POLA_dice_jax.py unverified MIT (permissive) · 2d3d1538bb6f1ad4 · report
dice_objective jax_files/POLA_dice_jax.py unverified MIT (permissive) · 77647113e31f6449 · report
dice_objective_plus_value_loss jax_files/POLA_dice_jax.py unverified MIT (permissive) · ed1c009c2edc43b1 · report
do_env_rollout jax_files/POLA_dice_jax.py unverified MIT (permissive) · 62939c089f70f346 · report
env_step jax_files/POLA_dice_jax.py unverified MIT (permissive) · 4d53c9d04908d6ae · report
get_gae_advantages jax_files/POLA_dice_jax.py unverified MIT (permissive) · 9e8f3bdffe71694b · report
get_init_hidden_states jax_files/POLA_dice_jax.py unverified MIT (permissive) · 42a79b923fa6137e · report
get_policies_for_states jax_files/POLA_dice_jax.py unverified MIT (permissive) · ea546e2113020484 · report
in_lookahead jax_files/POLA_dice_jax.py unverified MIT (permissive) · ce0d8c80b05c9add · report
update_gae_with_delta_backwards jax_files/POLA_dice_jax.py unverified MIT (permissive) · 2f998934ffa142d3 · report
value_loss jax_files/POLA_dice_jax.py unverified MIT (permissive) · 063b9d334804c7ce · report
alshedivat/lola found in paper text by Syntology 1 sample, 0 ran · 1 unverified
ExactLOLA lola/exact.py unverified MIT (permissive) · 0c013af22fc97f3a · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

2 assemblies on this paper: 1 harvested, 1 generated.

generated Assembly for Proximal Learning With Opponent-Learning Awareness (POLA) (graph method: Proximal Learning With Opponent-Learning Awareness (POLA)), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 3; 5 property tests passed on both).

label matches by construction: the code was generated for this method (not judged by a model)

  1. pola_dice_gradient_step entry · level 3 · ran · violated contract · 1e99f4650b9699bc8be66f564d295ca380d89d9b30c6b73920dc6b69fd93938a

harvested Assembly for Proximal Learning With Opponent-Learning Awareness (POLA) (graph method: Proximal Learning With Opponent-Learning Awareness (POLA)). 16 bricks; individually on a fixture: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 12 unverified. The assembly has not been run end-to-end.

  1. in_lookahead entry · level 0 · unverified · ce0d8c80b05c9add
  2. act sampler · level 0 · unverified · 80d4ccc33bef2e8a
  3. dice_objective_plus_value_loss helper · level 0 · unverified · ed1c009c2edc43b1
  4. do_env_rollout sampler · level 0 · unverified · 62939c089f70f346
  5. get_policies_for_states helper · level 0 · unverified · ea546e2113020484
  6. kl_div_jax metric · level 1 · ran · honoured contract · 70a992b1af899b2d
  7. rev_kl_div_jax metric · level 1 · ran · honoured contract · 54e852578016625d
  8. dice_objective loss · level 0 · unverified · 77647113e31f6449
  9. value_loss loss · level 0 · unverified · 063b9d334804c7ce
  10. env_step helper · level 0 · unverified · 4d53c9d04908d6ae
  11. get_init_hidden_states helper · level 0 · unverified · 42a79b923fa6137e
  12. act_w_iter_over_obs helper · level 0 · unverified · 2d3d1538bb6f1ad4
  13. get_gae_advantages helper · level 0 · unverified · 9e8f3bdffe71694b
  14. magic_box helper · level 1 · ran · honoured contract · f4166f1f2230b2e7
  15. reverse_cumsum helper · level 1 · ran · our draft was wrong · 61e0eb0133131d4c
  16. update_gae_with_delta_backwards helper · level 0 · unverified · 2f998934ffa142d3

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2210.10125") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Multi-agent Reinforcement Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections