SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.15567 · ICML · 2024

Foundation Policies with Hilbert Representations

Sergey Levine, Seohong Park, Tobias Kreiman

arXiv · PDF · Open in the Atlas

Code that ran

7 of 16 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 4 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 9 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/2402.15567.json · badge: /api/ran/2402.15567.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
seohongpark/hilp canonical (classifier label)
classifier basis not recorded on the link
7 ran · 9 no recorded run
FunctionStatusWhere it lives
get_canvas_image Ran
ran, honoured the contract we drafted
seohongpark/hilp/hilp_gcrl/src/d4rl_ant.py
pointer only (licence: NONE); the stored copy get_code serves, from seohongpark/HILP, is pointer only (licence: NONE) · get_code("2d17f9689108389d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, seohongpark/hilp 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.

get_keys Ran
ran; our contract draft was wrong, not the code
seohongpark/hilp/hilp_gcrl/d4rl_ext/offline_env.py
pointer only (licence: NONE); the stored copy get_code serves, from seohongpark/HILP, is pointer only (licence: NONE) · get_code("395635db622171fa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, seohongpark/hilp 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.

get_normalization Ran
ran, honoured the contract we drafted
seohongpark/hilp/hilp_gcrl/src/d4rl_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from seohongpark/HILP, is pointer only (licence: NONE) · get_code("e60bfdd0574ddc5f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, seohongpark/hilp 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.

kitchen_render Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
seohongpark/hilp/hilp_gcrl/dataset_render.py
pointer only (licence: NONE); the stored copy get_code serves, from seohongpark/HILP, is pointer only (licence: NONE) · get_code("56f8ab2680a5bf38")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, seohongpark/hilp 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.

most_squarelike Ran
ran, honoured the contract we drafted
seohongpark/hilp/hilp_gcrl/src/viz_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from seohongpark/HILP, is pointer only (licence: NONE) · get_code("fd2c92d2074f0195")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, seohongpark/hilp 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.

random_crop Ran
ran; our contract draft was wrong, not the code
seohongpark/hilp/hilp_gcrl/src/dataset_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from seohongpark/HILP, is pointer only (licence: NONE) · get_code("6ee7e4a795696bca")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, seohongpark/hilp 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.

valid_goal_sampler Ran
ran, honoured the contract we drafted
seohongpark/hilp/hilp_gcrl/src/d4rl_ant.py
pointer only (licence: NONE); the stored copy get_code serves, from seohongpark/HILP, is pointer only (licence: NONE) · get_code("a5514c312d961e08")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, seohongpark/hilp 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.

download_dataset_from_url Not yet run
unverified (harvested, no recorded run)
seohongpark/hilp/hilp_gcrl/d4rl_ext/offline_env.py
pointer only (licence: NONE) · get_code("88d6d21f699682b1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, seohongpark/hilp 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.

ensemblize Not yet run
unverified (harvested, no recorded run)
seohongpark/hilp/hilp_gcrl/jaxrl_m/networks.py
pointer only (licence: NONE); the stored copy get_code serves, from seohongpark/HILP, is pointer only (licence: NONE) · get_code("7f174e0d2fe49c08")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, seohongpark/hilp 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.

filepath_from_url Not yet run
unverified (harvested, no recorded run)
seohongpark/hilp/hilp_gcrl/d4rl_ext/offline_env.py
pointer only (licence: NONE) · get_code("e14321aa0b5c0b78")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, seohongpark/hilp 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.

make_env Not yet run
unverified (harvested, no recorded run)
seohongpark/hilp/hilp_gcrl/src/d4rl_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from seohongpark/HILP, is pointer only (licence: NONE) · get_code("b3d75720ab55c2c2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, seohongpark/hilp 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.

make_visual Not yet run
unverified (harvested, no recorded run)
seohongpark/hilp/hilp_gcrl/src/viz_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from seohongpark/HILP, is pointer only (licence: NONE) · get_code("9e273495210cbc4c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, seohongpark/hilp 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.

make_visual_no_image Not yet run
unverified (harvested, no recorded run)
seohongpark/hilp/hilp_gcrl/src/viz_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from seohongpark/HILP, is pointer only (licence: NONE) · get_code("8bc4244b8915e237")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, seohongpark/hilp 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.

prepare_video Not yet run
unverified (harvested, no recorded run)
seohongpark/hilp/hilp_gcrl/src/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from seohongpark/HILP, is pointer only (licence: NONE) · get_code("7effca8e608209f2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, seohongpark/hilp 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.

record_video Not yet run
unverified (harvested, no recorded run)
seohongpark/hilp/hilp_gcrl/src/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from seohongpark/HILP, is pointer only (licence: NONE) · get_code("8620eae358ce25cb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, seohongpark/hilp 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.

save_video Not yet run
unverified (harvested, no recorded run)
seohongpark/hilp/hilp_gcrl/src/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from seohongpark/HILP, is pointer only (licence: NONE) · get_code("61a1ee7ea522bbd8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, seohongpark/hilp 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 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 16 are also present in other papers whose code we hold (11 with at least one paper dated earlier, 2 the same month, 16 later) and 0 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.

FunctionAlso present inEarliest-datedOthers named
ensemblize 6 other papers
1 dated earlier, 1 the same month, 4 later · 2 only as an assembly brick
2307.11949 (2023-07)
HIQL: Offline Goal-Conditioned RL with Latent States as Actions
2402.17135 (2024-02)
Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings
2406.09329 (2024-06)
Is Value Learning Really the Main Bottleneck in Offline RL?
and 3 more not named here
filepath_from_url 6 other papers
4 dated earlier, 2 later
2004.07219 (2020-04)
D4RL: Datasets for Deep Data-Driven Reinforcement Learning
2211.09817 (2022-11)
On the Effect of Pre-training for Transformer in Different Modality on Offline Reinforcement Learning
2306.09303 (2023-06)
Datasets and Benchmarks for Offline Safe Reinforcement Learning
and 3 more not named here
get_keys 6 other papers
4 dated earlier, 2 later
2004.07219 (2020-04)
D4RL: Datasets for Deep Data-Driven Reinforcement Learning
2211.09817 (2022-11)
On the Effect of Pre-training for Transformer in Different Modality on Offline Reinforcement Learning
2306.09303 (2023-06)
Datasets and Benchmarks for Offline Safe Reinforcement Learning
and 3 more not named here
download_dataset_from_url 4 other papers
3 dated earlier, 1 later
2004.07219 (2020-04)
D4RL: Datasets for Deep Data-Driven Reinforcement Learning
2211.09817 (2022-11)
On the Effect of Pre-training for Transformer in Different Modality on Offline Reinforcement Learning
2312.01473 (2023-12)
Regularity as Intrinsic Reward for Free Play
and 1 more not named here
get_canvas_image 4 other papers
2 dated earlier, 1 the same month, 1 later
2304.04782 (2023-04)
Reinforcement Learning from Passive Data via Latent Intentions
2307.11949 (2023-07)
HIQL: Offline Goal-Conditioned RL with Latent States as Actions
2402.17135 (2024-02)
Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings
and 1 more not named here
get_normalization 3 other papers
2 dated earlier, 1 later
2304.04782 (2023-04)
Reinforcement Learning from Passive Data via Latent Intentions
2307.11949 (2023-07)
HIQL: Offline Goal-Conditioned RL with Latent States as Actions
2510.15382 (2025-10)
Towards Robust Zero-Shot Reinforcement Learning
valid_goal_sampler 3 other papers
2 dated earlier, 1 later
2304.04782 (2023-04)
Reinforcement Learning from Passive Data via Latent Intentions
2307.11949 (2023-07)
HIQL: Offline Goal-Conditioned RL with Latent States as Actions
2510.15382 (2025-10)
Towards Robust Zero-Shot Reinforcement Learning
make_visual 2 other papers
1 dated earlier, 1 later
2307.11949 (2023-07)
HIQL: Offline Goal-Conditioned RL with Latent States as Actions
2510.15382 (2025-10)
Towards Robust Zero-Shot Reinforcement Learning
make_visual_no_image 2 other papers
1 dated earlier, 1 later
2307.11949 (2023-07)
HIQL: Offline Goal-Conditioned RL with Latent States as Actions
2510.15382 (2025-10)
Towards Robust Zero-Shot Reinforcement Learning
most_squarelike 2 other papers
1 dated earlier, 1 later
2307.11949 (2023-07)
HIQL: Offline Goal-Conditioned RL with Latent States as Actions
2510.15382 (2025-10)
Towards Robust Zero-Shot Reinforcement Learning
save_video 2 other papers
1 dated earlier, 1 later
2307.11949 (2023-07)
HIQL: Offline Goal-Conditioned RL with Latent States as Actions
2510.15382 (2025-10)
Towards Robust Zero-Shot Reinforcement Learning
kitchen_render 1 other paper
1 later
2510.15382 (2025-10)
Towards Robust Zero-Shot Reinforcement Learning
make_env 1 other paper
1 later
2510.15382 (2025-10)
Towards Robust Zero-Shot Reinforcement Learning
prepare_video 1 other paper
1 later
2510.15382 (2025-10)
Towards Robust Zero-Shot Reinforcement Learning
random_crop 1 other paper
1 later
2510.15382 (2025-10)
Towards Robust Zero-Shot Reinforcement Learning
record_video 1 other paper
1 later
2510.15382 (2025-10)
Towards Robust Zero-Shot Reinforcement Learning

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

Unsupervised and self-supervised objectives, such as next token prediction, have enabled pretraining generalist models from large amounts of unlabeled data. In reinforcement learning (RL), however, finding a truly general and scalable unsupervised pre-training objective for generalist policies from offline data remains a major open question. While a number of methods have been proposed to enable generic self-supervised RL, based on principles such as goal-conditioned RL, behavioral cloning, and unsupervised skill learning, such methods remain limited in terms of either the diversity of the discovered behaviors, the need for high-quality demonstration data, or the lack of a clear adaptation mechanism for downstream tasks. In this work, we propose a novel unsupervised framework to pre-train generalist policies that capture diverse, optimal, long-horizon behaviors from unlabeled offline data such that they can be quickly adapted to any arbitrary new tasks in a zero-shot manner. Our key insight is to learn a structured representation that preserves the temporal structure of the underlying environment, and then to span this learned latent space with directional movements, which enables various zero-shot policy "prompting" schemes for downstream tasks. Through our experiments on simulated robotic locomotion and manipulation benchmarks, we show that our unsupervised policies can solve goal-conditioned and general RL tasks in a zero-shot fashion, even often outperforming prior methods designed specifically for each setting. Our code and videos are available at https: //seohong.me/projects/hilp/.

For agents

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

get_harvested_code_for_paper("2402.15567")
get_code_for_paper("2402.15567")
have("2402.15567")

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

curl https://syntology.ai/api/ran/2402.15567.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.15567.svg)](https://syntology.ai/paper/2402.15567)

Connect an agent — have() is free.