Papers › Generalization to New Actions in Reinforcement Learning

Generalization to New Actions in Reinforcement Learning

3 Nov 2020ICML 2020 1arXiv:2011.01928archive 2025-07-28

Ayush Jain, Andrew Szot, Joseph J. Lim

A fundamental trait of intelligence is the ability to achieve goals in the face of novel circumstances, such as making decisions from new action choices. However, standard reinforcement learning assumes a fixed set of actions and requires expensive retraining when given a new action set. To make learning agents more adaptable, we introduce the problem of zero-shot generalization to new actions. We propose a two-stage framework where the agent first infers action representations from action information acquired separately from the task. A policy flexible to varying action sets is then trained with generalization objectives. We benchmark generalization on sequential tasks, such as selecting from an unseen tool-set to solve physical reasoning puzzles and stacking towers with novel 3D shapes. Videos and code are available at https://sites.google.com/view/action-generalization

PaperPDFConference PDFCodeCode 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 21 code samples harvested from 2 repositories linked to this paper: 18 ran (of which 14 constructed an object rather than computing a result; 16 with no instrument failure: 2 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 21 samples from 2 repositories, 18 ran (16 with no instrument failure; 2 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.

clvrai/new-actions-rl officialmentioned in paperpytorchSyntology: 20 samples, 17 ran (1 instrument-failed) · 3 unverified report
clvrai/create officialSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 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

21 samples harvested: 18 ran (of which 14 constructed an object rather than computing a result; 16 with no instrument failure: 2 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 3 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.

2ran · honoured contract
2ran · our draft was wrong
14ran
3unverified

Licence: 20 of the 21 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”. For 7 samples 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.

clvrai/new-actions-rl official repository 20 samples, 17 ran (1 instrument-failed) · 3 unverified
Beta method/models/main_method.py ran · metamorphic tier: deterministic no licence file found · pointer only · 2549d67825e3fb58 · report fixture: returned Beta · level recorded 2026-09-22
CNNBase_NEW method/models/main_method.py ran · metamorphic tier: deterministic no licence file found · pointer only · dd4a9f0d253bfe90 · report fixture: returned CNNBase_NEW · level recorded 2026-09-22
Categorical in 6 papers method/models/main_method.py ran · metamorphic tier: deterministic no licence file found · pointer only · 2e0973cb87fadfb6 · report fixture: returned Categorical · level recorded 2026-09-22
ConditionedAuxDist method/models/main_method.py ran · metamorphic tier: deterministic no licence file found · pointer only · 93b65a059eba1be7 · report fixture: returned ConditionedAuxDist · level recorded 2026-09-22
ConditionedAuxWrapper method/models/main_method.py ran no licence file found · pointer only · c2bdefbcdfe3a875 · report fixture: returned ConditionedAuxWrapper · level recorded 2026-09-22
Conv2d3x3 method/models/main_method.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 2062968c588d48da · report fixture: returned Conv2d3x3 · level recorded 2026-09-22
DiagGaussian method/models/main_method.py ran · metamorphic tier: deterministic no licence file found · pointer only · c3e91ef2c04afa28 · report fixture: returned DiagGaussian · level recorded 2026-09-22
DiagGaussianVariance method/models/main_method.py ran · metamorphic tier: deterministic no licence file found · pointer only · 91666da04aaa6ba4 · report fixture: returned DiagGaussianVariance · level recorded 2026-09-22
DistWrapper method/models/main_method.py ran no licence file found · pointer only · c72079105e05daaa · report fixture: returned DistWrapper · level recorded 2026-09-22
MLPBase method/models/main_method.py ran · metamorphic tier: deterministic no licence file found · pointer only · 0c518a49b21b3a37 · report fixture: returned MLPBase · level recorded 2026-09-22
MixedDist method/models/main_method.py ran · metamorphic tier: deterministic no licence file found · pointer only · 5ad49de4aa356408 · report fixture: returned MixedDist · level recorded 2026-09-22
NNBase method/models/main_method.py ran · metamorphic tier: deterministic no licence file found · pointer only · 4f7b9c26206107af · report fixture: returned NNBase · level recorded 2026-09-22
OrderInvariantCategorical method/models/main_method.py ran · metamorphic tier: deterministic no licence file found · pointer only · 5113f693aa39c008 · report fixture: returned OrderInvariantCategorical · level recorded 2026-09-22
RndCategorical method/models/main_method.py ran · metamorphic tier: deterministic no licence file found · pointer only · 08477ea65294ed85 · report fixture: returned RndCategorical · level recorded 2026-09-22
add_mag_stats method/models/main_method.py ran · our draft was wrong fingerprinted no licence file found · pointer only · c790bb0df379811f · report fixture: signature inferred_z:Tensor/2/float · returned dict · level recorded 2026-09-22
extract_aval method/models/main_method.py ran · honoured contract no licence file found · pointer only · 0e7b0c51b3d70736 · report fixture: signature extra:NoneType/0/?, infos:list/1/dict · returned Tensor · level recorded 2026-09-22
init_extract_aval method/models/main_method.py ran · honoured contract no licence file found · pointer only · 72d99a8e5cd83dc8 · report fixture: signature args:ArgsConfig/0/?, evaluate:bool/0/bool · returned Tensor · level recorded 2026-09-22
ActorCritic in 10 papers method/models/main_method.py unverified no licence file found · pointer only · 7da11c67fbcd655c · report
BasePolicy in 8 papers method/models/main_method.py unverified no licence file found · pointer only · e8e8cf08b831157a · report
MainMethod method/models/main_method.py unverified no licence file found · pointer only · e09457d2f83e11bc · report
clvrai/create official repository 1 sample, 1 ran (1 instrument-failed) · 0 unverified
split_action_set create_game/create_action_set.py ran · our draft was wrong fingerprinted MIT (permissive) · be293701f9986ccd · report fixture: signature test_set:list/1/str, validation_ratio:float/0/float · returned tuple · level recorded 2026-09-22

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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for two-stage framework (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for two-stage framework (graph method: two-stage framework). 22 bricks; individually on a fixture: 19 ran (of which 15 constructed an object rather than computing a result; 17 with no instrument failure: 2 honoured, 0 violated, 15 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. MainMethod entry · level 0 · unverified · e09457d2f83e11bc
  2. BasePolicy helper · level 0 · unverified · e8e8cf08b831157a
  3. Categorical helper · level 1 · ran · 2e0973cb87fadfb6
  4. OrderInvariantCategorical model · level 1 · ran · 5113f693aa39c008
  5. RndCategorical model · level 1 · ran · 08477ea65294ed85
  6. add_mag_stats helper · level 1 · ran · our draft was wrong · c790bb0df379811f
  7. extract_aval helper · level 1 · ran · honoured contract · 0e7b0c51b3d70736
  8. init_extract_aval helper · level 1 · ran · honoured contract · 72d99a8e5cd83dc8
  9. ActorCritic helper · level 0 · unverified · 7da11c67fbcd655c
  10. Beta helper · level 1 · ran · 2549d67825e3fb58
  11. ConditionedAuxDist helper · level 1 · ran · 93b65a059eba1be7
  12. DiagGaussian helper · level 1 · ran · c3e91ef2c04afa28
  13. DiagGaussianVariance helper · level 1 · ran · 91666da04aaa6ba4
  14. MixedDist helper · level 1 · ran · 5ad49de4aa356408
  15. init helper · level 1 · ran · our draft was wrong · 9de355e93051e4ad
  16. CNNBase_NEW helper · level 1 · ran · dd4a9f0d253bfe90
  17. MLPBase helper · level 1 · ran · 0c518a49b21b3a37
  18. ConditionedAuxWrapper helper · level 1 · ran · c2bdefbcdfe3a875
  19. AddBias helper · level 1 · ran · 6ea7d9f4a4c4f42d
  20. DistWrapper helper · level 1 · ran · c72079105e05daaa
  21. Conv2d3x3 helper · level 1 · ran · 2062968c588d48da
  22. NNBase helper · level 1 · ran · 4f7b9c26206107af

harvested Assembly for two-stage framework (graph method: two-stage framework). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. split_action_set entry · level 1 · ran · our draft was wrong · be293701f9986ccd

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="2011.01928") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Reinforcement LearningReinforcement Learning (RL)Zero-shot Generalizationreinforcement-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