Papers › Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual...

Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal Generation

12 Sep 2019ICLR 2020 1arXiv:1909.05829archive 2025-07-28

Suraj Nair, Chelsea Finn

Video prediction models combined with planning algorithms have shown promise in enabling robots to learn to perform many vision-based tasks through only self-supervision, reaching novel goals in cluttered scenes with unseen objects. However, due to the compounding uncertainty in long horizon video prediction and poor scalability of sampling-based planning optimizers, one significant limitation of these approaches is the ability to plan over long horizons to reach distant goals. To that end, we propose a framework for subgoal generation and planning, hierarchical visual foresight (HVF), which generates subgoal images conditioned on a goal image, and uses them for planning. The subgoal images are directly optimized to decompose the task into easy to plan segments, and as a result, we observe that the method naturally identifies semantically meaningful states as subgoals. Across three out of four simulated vision-based manipulation tasks, we find that our method achieves nearly a 200% performance improvement over planning without subgoals and model-free RL approaches. Further, our experiments illustrate that our approach extends to real, cluttered visual scenes. Project page: https://sites.google.com/stanford.edu/hvf

PaperPDFConference PDFCodeCode 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="1909.05829")

Code

Syntology Ran 0 of 19 code samples harvested from 1 repository linked to this paper; 19 have no recorded run.

By repository: official repository: 19 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.

suraj-nair-1/google-research officialmentioned on GitHubtfApache-2.0 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

19 samples harvested; 0 ran; 0 honoured the contract we drafted; 19 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.

19unverified

Licence: 0 of the 19 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 suraj-nair-1/google-research. “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.

call_max_payoff suraj-nair-1/google-research/simulation_research/tf_risk/payoffs.py official repository unverified Apache-2.0 (permissive) · 97547251dd8bf1ea · report
call_payoff suraj-nair-1/google-research/simulation_research/tf_risk/payoffs.py official repository unverified Apache-2.0 (permissive) · af5fe347cb6b1c21 · report
compute_normalization_fixed_point suraj-nair-1/google-research/bitempered_loss/loss.py official repository unverified Apache-2.0 (permissive) · 95c4de11b59394a7 · report
exp_t suraj-nair-1/google-research/bitempered_loss/loss.py official repository unverified Apache-2.0 (permissive) · 384b5cce28dc76a9 · report
gaussian_cdf suraj-nair-1/google-research/simulation_research/tf_risk/util.py official repository unverified Apache-2.0 (permissive) · c4e259e6f90e1040 · report
half_clt_conf_interval suraj-nair-1/google-research/simulation_research/tf_risk/util.py official repository unverified Apache-2.0 (permissive) · 06faedac0b5a7f7b · report
hedge_derivative suraj-nair-1/google-research/simulation_research/tf_risk/controllers.py official repository unverified Apache-2.0 (permissive) · b72e0f9ec4b4e65f · report
hist_log_euler_step suraj-nair-1/google-research/simulation_research/tf_risk/run_replication_experiment.py official repository unverified Apache-2.0 (permissive) · cc2b7edf2f6f80c7 · report
log_t suraj-nair-1/google-research/bitempered_loss/loss.py official repository unverified Apache-2.0 (permissive) · 4dc9301a54801f0a · report
multistep_runner_tf_while suraj-nair-1/google-research/simulation_research/tf_risk/monte_carlo_manager.py official repository unverified Apache-2.0 (permissive) · b4b4f1f2f73b76ca · report
multistep_runner_unrolled_tf suraj-nair-1/google-research/simulation_research/tf_risk/monte_carlo_manager.py official repository unverified Apache-2.0 (permissive) · aeb9ddd5a60dd753 · report
non_callable_price_mc suraj-nair-1/google-research/simulation_research/tf_risk/monte_carlo_manager.py official repository unverified Apache-2.0 (permissive) · 18ed7c75e6ad4c0c · report
price_derivative suraj-nair-1/google-research/simulation_research/tf_risk/controllers.py official repository unverified Apache-2.0 (permissive) · 934448b79596475e · report
put_payoff suraj-nair-1/google-research/simulation_research/tf_risk/payoffs.py official repository unverified Apache-2.0 (permissive) · c3a241a17bb8b5ec · report
random_antithetic_uniform suraj-nair-1/google-research/simulation_research/tf_risk/dynamics.py official repository unverified Apache-2.0 (permissive) · 9834d99dd9e09ef2 · report
random_normal suraj-nair-1/google-research/simulation_research/tf_risk/dynamics.py official repository unverified Apache-2.0 (permissive) · 4ece14378ed96542 · report
random_uniform suraj-nair-1/google-research/simulation_research/tf_risk/dynamics.py official repository unverified Apache-2.0 (permissive) · 07c5675970cb9ee8 · report
stddev_est suraj-nair-1/google-research/simulation_research/tf_risk/util.py official repository unverified Apache-2.0 (permissive) · 3f5e10b1b3013170 · report
var_and_cvar suraj-nair-1/google-research/simulation_research/tf_risk/risk_metrics.py official repository unverified Apache-2.0 (permissive) · 813daf1432469b53 · report

Tasks

Self-Supervised LearningVideo Prediction

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