Papers › Instance based Generalization in Reinforcement Learning

Instance based Generalization in Reinforcement Learning

2 Nov 2020arXiv:2011.01089archive 2025-07-28

Martin Bertran, Natalia Martinez, Mariano Phielipp, Guillermo Sapiro

Agents trained via deep reinforcement learning (RL) routinely fail to generalize to unseen environments, even when these share the same underlying dynamics as the training levels. Understanding the generalization properties of RL is one of the challenges of modern machine learning. Towards this goal, we analyze policy learning in the context of Partially Observable Markov Decision Processes (POMDPs) and formalize the dynamics of training levels as instances. We prove that, independently of the exploration strategy, reusing instances introduces significant changes on the effective Markov dynamics the agent observes during training. Maximizing expected rewards impacts the learned belief state of the agent by inducing undesired instance specific speedrunning policies instead of generalizeable ones, which are suboptimal on the training set. We provide generalization bounds to the value gap in train and test environments based on the number of training instances, and use insights based on these to improve performance on unseen levels. We propose training a shared belief representation over an ensemble of specialized policies, from which we compute a consensus policy that is used for data collection, disallowing instance specific exploitation. We experimentally validate our theory, observations, and the proposed computational solution over the CoinRun benchmark.

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.

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

Code

Syntology 7 code samples harvested from 1 repository linked to this paper: 6 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 7 samples from 1 repository, 6 ran (5 with no instrument failure; 1 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.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

MartinBertran/InstanceAgnosticPolicyEnsembles officialmentioned in paperpytorchSyntology: 7 samples, 6 ran (1 instrument-failed) · 1 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.

Code Syntology ran Syntology

7 samples harvested: 6 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 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.

1ran · violated contract
1ran · our draft was wrong
4ran
1unverified

Licence: 7 of the 7 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 MartinBertran/InstanceAgnosticPolicyEnsembles. “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”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

MartinBertran/InstanceAgnosticPolicyEnsembles official repository 7 samples, 6 ran (1 instrument-failed) · 1 unverified
ImpalaCNN iape/iape/backend/core.py ran GPL-3.0 (copyleft) · pointer only · 5cf1dfb12135d362 · report fixture: returned ImpalaCNN · level recorded 2026-09-22
MetaBlock in 5 papers iape/iape/backend/core.py ran fingerprinted GPL-3.0 (copyleft) · pointer only · 62359dcd1406afdf · report fixture: returned MetaBlock · level recorded 2026-09-22
RNNWDAbridgedModel iape/iape/backend/core.py ran GPL-3.0 (copyleft) · pointer only · d2087f8eab5cbb06 · report fixture: returned RNNWDAbridgedModel · level recorded 2026-09-22
ResidualBlock in 100 papers iape/iape/backend/core.py ran GPL-3.0 (copyleft) · pointer only · 3d5dd3f37271653c · report fixture: returned ResidualBlock · level recorded 2026-09-22
conv_output_shape in 8 papers iape/iape/backend/core.py ran · violated contract GPL-3.0 (copyleft) · pointer only · c2f750d2cc520160 · report fixture: signature h_w:tuple/1/int, kernel_size:int/0/int, stride:int/0/int, pad:int/0/int, dilation:int/0/int · returned tuple · level recorded 2026-09-22
max2d_output_shape iape/iape/backend/core.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · b2e23f1141df862a · report fixture: signature h_w:tuple/1/int, kernel_size:int/0/int, stride:int/0/int, pad:int/0/int, dilation:int/0/int · returned tuple · level recorded 2026-09-22
RNNAbridgedActorCritic iape/iape/backend/core.py unverified GPL-3.0 (copyleft) · pointer only · 798b8adfc3fb11f0 · 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. 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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for training a shared belief representation over an ensemble of specialized policies (graph method: training a shared belief representation over an ensemble of specialized policies). 7 bricks; individually on a fixture: 6 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

  1. RNNAbridgedActorCritic entry · level 0 · unverified · 798b8adfc3fb11f0
  2. ImpalaCNN helper · level 1 · ran · 5cf1dfb12135d362
  3. RNNWDAbridgedModel model · level 1 · ran · d2087f8eab5cbb06
  4. MetaBlock helper · level 1 · ran · 62359dcd1406afdf
  5. ResidualBlock helper · level 1 · ran · 3d5dd3f37271653c
  6. conv_output_shape helper · level 1 · ran · violated contract · c2f750d2cc520160
  7. max2d_output_shape helper · level 1 · ran · our draft was wrong · b2e23f1141df862a

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="2011.01089") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Deep Reinforcement LearningGeneralization BoundsReinforcement LearningReinforcement Learning (RL)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