SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2011.01928 · ICML · 2020

Generalization to New Actions in Reinforcement Learning

Ayush Jain, Andrew Szot, Joseph Lim

arXiv · PDF · Open in the Atlas

Code that ran

18 of 21 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (14 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 14 have no contract verdict; 2 failures of our instrument; 3 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/2011.01928.json · badge: /api/ran/2011.01928.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
clvrai/new-actions-rl canonical (classifier label)
classifier basis: classifier_2025
17 ran · 3 no recorded run
clvrai/create marked official in Papers with Code
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
Beta Ran
ran on a synthesized input · constructed an object; no result was computed
clvrai/new-actions-rl/method/models/main_method.py
pointer only (licence: NONE) · get_code("2549d67825e3fb58")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clvrai/new-actions-rl 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.

CNNBase_NEW Ran
ran on a synthesized input · constructed an object; no result was computed
clvrai/new-actions-rl/method/models/main_method.py
pointer only (licence: NONE) · get_code("dd4a9f0d253bfe90")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clvrai/new-actions-rl 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.

Categorical Ran
ran on a synthesized input · constructed an object; no result was computed
clvrai/new-actions-rl/method/models/main_method.py
pointer only (licence: NONE) · get_code("2e0973cb87fadfb6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clvrai/new-actions-rl 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.

ConditionedAuxDist Ran
ran on a synthesized input · constructed an object; no result was computed
clvrai/new-actions-rl/method/models/main_method.py
pointer only (licence: NONE) · get_code("93b65a059eba1be7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clvrai/new-actions-rl 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.

ConditionedAuxWrapper Ran
ran on a synthesized input · constructed an object; no result was computed
clvrai/new-actions-rl/method/models/main_method.py
pointer only (licence: NONE) · get_code("c2bdefbcdfe3a875")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clvrai/new-actions-rl 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.

Conv2d3x3 Ran
ran on a synthesized input · constructed an object; no result was computed
clvrai/new-actions-rl/method/models/main_method.py
pointer only (licence: NONE) · get_code("2062968c588d48da")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clvrai/new-actions-rl 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.

DiagGaussian Ran
ran on a synthesized input · constructed an object; no result was computed
clvrai/new-actions-rl/method/models/main_method.py
pointer only (licence: NONE) · get_code("c3e91ef2c04afa28")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clvrai/new-actions-rl 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.

DiagGaussianVariance Ran
ran on a synthesized input · constructed an object; no result was computed
clvrai/new-actions-rl/method/models/main_method.py
pointer only (licence: NONE) · get_code("91666da04aaa6ba4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clvrai/new-actions-rl 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.

DistWrapper Ran
ran on a synthesized input · constructed an object; no result was computed
clvrai/new-actions-rl/method/models/main_method.py
pointer only (licence: NONE) · get_code("c72079105e05daaa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clvrai/new-actions-rl 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.

MLPBase Ran
ran on a synthesized input · constructed an object; no result was computed
clvrai/new-actions-rl/method/models/main_method.py
pointer only (licence: NONE) · get_code("0c518a49b21b3a37")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clvrai/new-actions-rl 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.

MixedDist Ran
ran on a synthesized input · constructed an object; no result was computed
clvrai/new-actions-rl/method/models/main_method.py
pointer only (licence: NONE) · get_code("5ad49de4aa356408")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clvrai/new-actions-rl 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.

NNBase Ran
ran on a synthesized input · constructed an object; no result was computed
clvrai/new-actions-rl/method/models/main_method.py
pointer only (licence: NONE) · get_code("4f7b9c26206107af")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clvrai/new-actions-rl 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.

OrderInvariantCategorical Ran
ran on a synthesized input · constructed an object; no result was computed
clvrai/new-actions-rl/method/models/main_method.py
pointer only (licence: NONE) · get_code("5113f693aa39c008")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clvrai/new-actions-rl 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.

RndCategorical Ran
ran on a synthesized input · constructed an object; no result was computed
clvrai/new-actions-rl/method/models/main_method.py
pointer only (licence: NONE) · get_code("08477ea65294ed85")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clvrai/new-actions-rl 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.

add_mag_stats Ran
ran; our contract draft was wrong, not the code
clvrai/new-actions-rl/method/models/main_method.py
pointer only (licence: NONE) · get_code("c790bb0df379811f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clvrai/new-actions-rl 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.

extract_aval Ran
ran, honoured the contract we drafted
clvrai/new-actions-rl/method/models/main_method.py
pointer only (licence: NONE) · get_code("0e7b0c51b3d70736")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clvrai/new-actions-rl 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.

init_extract_aval Ran
ran, honoured the contract we drafted
clvrai/new-actions-rl/method/models/main_method.py
pointer only (licence: NONE) · get_code("72d99a8e5cd83dc8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clvrai/new-actions-rl 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.

split_action_set Ran
ran; our contract draft was wrong, not the code
clvrai/create/create_game/create_action_set.py
code served (permissive licence) · get_code("be293701f9986ccd")
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) and returned tuple. 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 numpy as np

# Construct test_set as a list of simple items (strings, dicts, or numbers)
# The function uses: indexing (test_set[:]), len(), and shuffle()
# So test_set must be a list-like object
test_set = ['action_1', 'action_2', 'action_3', 'action_4', 'action_5']

# validation_ratio is a float between 0 and 1
validation_ratio = 0.4

ARGS = {
    'test_set': test_set,
    'validation_ratio': validation_ratio
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
ActorCritic Not yet run
unverified (harvested, no recorded run)
clvrai/new-actions-rl/method/models/main_method.py
pointer only (licence: NONE) · get_code("7da11c67fbcd655c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clvrai/new-actions-rl 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. No invocation recorded.

BasePolicy Not yet run
unverified (harvested, no recorded run)
clvrai/new-actions-rl/method/models/main_method.py
pointer only (licence: NONE) · get_code("e8e8cf08b831157a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clvrai/new-actions-rl 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. No invocation recorded.

MainMethod Not yet run
unverified (harvested, no recorded run)
clvrai/new-actions-rl/method/models/main_method.py
pointer only (licence: NONE) · get_code("e09457d2f83e11bc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, clvrai/new-actions-rl 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. No invocation recorded.

Also present in other papers' code

Of 21 samples lifted from this paper's linked repositories, 21 carry a function identity and 0 do not. Of the 21 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 21 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

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.

For agents

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

get_harvested_code_for_paper("2011.01928")
get_code_for_paper("2011.01928")
have("2011.01928")

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

curl https://syntology.ai/api/ran/2011.01928.json

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

[![Syntology run record](https://syntology.ai/api/ran/2011.01928.svg)](https://syntology.ai/paper/2011.01928)

Connect an agent — have() is free.