Papers › Learning Latent Dynamics for Planning from Pixels

Learning Latent Dynamics for Planning from Pixels

12 Nov 2018arXiv:1811.04551archive 2025-07-28

Danijar Hafner, Timothy Lillicrap, Ian Fischer, Ruben Villegas, David Ha, Honglak Lee, James Davidson

Planning has been very successful for control tasks with known environment dynamics. To leverage planning in unknown environments, the agent needs to learn the dynamics from interactions with the world. However, learning dynamics models that are accurate enough for planning has been a long-standing challenge, especially in image-based domains. We propose the Deep Planning Network (PlaNet), a purely model-based agent that learns the environment dynamics from images and chooses actions through fast online planning in latent space. To achieve high performance, the dynamics model must accurately predict the rewards ahead for multiple time steps. We approach this using a latent dynamics model with both deterministic and stochastic transition components. Moreover, we propose a multi-step variational inference objective that we name latent overshooting. Using only pixel observations, our agent solves continuous control tasks with contact dynamics, partial observability, and sparse rewards, which exceed the difficulty of tasks that were previously solved by planning with learned models. PlaNet uses substantially fewer episodes and reaches final performance close to and sometimes higher than strong model-free algorithms.

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="1811.04551")

Code

Syntology Ran 2 of 7 code samples harvested from 5 repositories linked to this paper; 5 have no recorded run. Of those that ran: 2 ran with no contract checked.

By repository: official repository: 3 samples from 1 repository, 0 ran; community (archive-listed): 4 samples from 4 repositories, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

google-research/planet officialmentioned on GitHubtfApache-2.0 report
Kaixhin/PlaNet mentioned on GitHubpytorch report
Yizhao111/dreamer-pytorch mentioned on GitHubpytorch report
chandar-lab/LoCA2 mentioned on GitHubtf report
cross32768/PlaNet_PyTorch mentioned on GitHubpytorch report
juliuskunze/cwvae-jax mentioned on GitHubjax report
simonzhan-code/step-wise_saferl_pixel mentioned on GitHubpytorch report
vaibhavsaxena11/cwvae mentioned on GitHubtf report
xingyu-lin/softagent mentioned on GitHubpytorch 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

7 samples harvested; 2 ran; 0 honoured the contract we drafted; 5 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.

2ran
5unverified

Licence: 1 of the 7 samples is 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 5 repositories linked to this paper, official or community; each sample names its own and says which. “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.

discounted_return google-research/planet/planet/control/temporal_difference.py official repository unverified Apache-2.0 (permissive) · e0037b2b9ff475af · report
fixed_step_return google-research/planet/planet/control/temporal_difference.py official repository unverified Apache-2.0 (permissive) · 5ebd8ca0b33c28d7 · report
lambda_return google-research/planet/planet/control/temporal_difference.py official repository unverified Apache-2.0 (permissive) · e437c521c0aeb696 · report
RecurrentStateSpaceModel cross32768/PlaNet_PyTorch/model.py community (archive-listed) ran MIT (permissive) · 5c38c6ed046ae967 · report
TransitionModel xingyu-lin/softagent/planet/models.py community (archive-listed) ran · metamorphic tier: deterministic no licence file found · pointer only · efe7f713034a1846 · report
TransitionModel Kaixhin/PlaNet/models.py community (archive-listed) unverified MIT (permissive) · c2d4d65f835c80d5 · report
TransitionModel Yizhao111/dreamer-pytorch/models.py community (archive-listed) unverified MIT (permissive) · c2cbf0fc5d0dc1a5 · report

Tasks

Continuous ControlMotion PlanningVariational Inferencecontinuous-control

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Continuous Control DeepMind Cup Catch (Images) PlaNet Return 914 #2 of 2 Archive leaderboard report
Continuous Control DeepMind Walker Walk (Images) PlaNet Return 890 #2 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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