Papers › Foundation Policies with Hilbert Representations

Foundation Policies with Hilbert Representations

23 Feb 2024arXiv:2402.15567archive 2025-07-28

Seohong Park, Tobias Kreiman, Sergey Levine

Unsupervised and self-supervised objectives, such as next token prediction, have enabled pre-training 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/.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2402.15567")

Code

Syntology Ran 0 of 16 code samples harvested from 1 repository linked to this paper; 16 have no recorded run.

By repository: official repository: 16 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

seohongpark/hilp officialmentioned in paperjax report
rail-berkeley/supe mentioned on GitHubjaxMIT 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

16 samples harvested; 0 ran; 0 honoured the contract we drafted; 16 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

16unverified

Licence: 16 of the 16 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 seohongpark/hilp. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

download_dataset_from_url seohongpark/hilp/hilp_gcrl/d4rl_ext/offline_env.py official repository unverified no licence file found · pointer only · 88d6d21f699682b1 · report
ensemblize seohongpark/hilp/hilp_gcrl/jaxrl_m/networks.py official repository unverified no licence file found · pointer only · 7f174e0d2fe49c08 · report
filepath_from_url seohongpark/hilp/hilp_gcrl/d4rl_ext/offline_env.py official repository unverified no licence file found · pointer only · e14321aa0b5c0b78 · report
get_canvas_image seohongpark/hilp/hilp_gcrl/src/d4rl_ant.py official repository unverified no licence file found · pointer only · 2d17f9689108389d · report
get_keys seohongpark/hilp/hilp_gcrl/d4rl_ext/offline_env.py official repository unverified no licence file found · pointer only · 395635db622171fa · report
get_normalization seohongpark/hilp/hilp_gcrl/src/d4rl_utils.py official repository unverified no licence file found · pointer only · e60bfdd0574ddc5f · report
kitchen_render seohongpark/hilp/hilp_gcrl/dataset_render.py official repository unverified no licence file found · pointer only · 56f8ab2680a5bf38 · report
make_env seohongpark/hilp/hilp_gcrl/src/d4rl_utils.py official repository unverified no licence file found · pointer only · b3d75720ab55c2c2 · report
make_visual seohongpark/hilp/hilp_gcrl/src/viz_utils.py official repository unverified no licence file found · pointer only · 9e273495210cbc4c · report
make_visual_no_image seohongpark/hilp/hilp_gcrl/src/viz_utils.py official repository unverified no licence file found · pointer only · 8bc4244b8915e237 · report
most_squarelike seohongpark/hilp/hilp_gcrl/src/viz_utils.py official repository unverified no licence file found · pointer only · fd2c92d2074f0195 · report
prepare_video seohongpark/hilp/hilp_gcrl/src/utils.py official repository unverified no licence file found · pointer only · 7effca8e608209f2 · report
random_crop seohongpark/hilp/hilp_gcrl/src/dataset_utils.py official repository unverified no licence file found · pointer only · 6ee7e4a795696bca · report
record_video seohongpark/hilp/hilp_gcrl/src/utils.py official repository unverified no licence file found · pointer only · 8620eae358ce25cb · report
save_video seohongpark/hilp/hilp_gcrl/src/utils.py official repository unverified no licence file found · pointer only · 61a1ee7ea522bbd8 · report
valid_goal_sampler seohongpark/hilp/hilp_gcrl/src/d4rl_ant.py official repository unverified no licence file found · pointer only · a5514c312d961e08 · report

Tasks

Reinforcement Learning (RL)Unsupervised Pre-training

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