Papers › Discrete Codebook World Models for Continuous Control

Discrete Codebook World Models for Continuous Control

1 Mar 2025arXiv:2503.00653archive 2025-07-28

Aidan Scannell, Mohammadreza Nakhaei, Kalle Kujanpää, Yi Zhao, Kevin Sebastian Luck, Arno Solin, Joni Pajarinen

In reinforcement learning (RL), world models serve as internal simulators, enabling agents to predict environment dynamics and future outcomes in order to make informed decisions. While previous approaches leveraging discrete latent spaces, such as DreamerV3, have demonstrated strong performance in discrete action settings and visual control tasks, their comparative performance in state-based continuous control remains underexplored. In contrast, methods with continuous latent spaces, such as TD-MPC2, have shown notable success in state-based continuous control benchmarks. In this paper, we demonstrate that modeling discrete latent states has benefits over continuous latent states and that discrete codebook encodings are more effective representations for continuous control, compared to alternative encodings, such as one-hot and label-based encodings. Based on these insights, we introduce DCWM: Discrete Codebook World Model, a self-supervised world model with a discrete and stochastic latent space, where latent states are codes from a codebook. We combine DCWM with decision-time planning to get our model-based RL algorithm, named DC-MPC: Discrete Codebook Model Predictive Control, which performs competitively against recent state-of-the-art algorithms, including TD-MPC2 and DreamerV3, on continuous control benchmarks. See our project website www.aidanscannell.com/dcmpc.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 8 code samples harvested from 1 repository linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 8 samples from 1 repository, 6 ran (6 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

aidanscannell/dcmpc officialpytorchMITSyntology: 8 samples, 6 ran (0 instrument-failed) · 2 unverified 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

8 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

6ran
2unverified

Licence: 0 of the 8 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 aidanscannell/dcmpc. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

aidanscannell/dcmpc official repository 8 samples, 6 ran (0 instrument-failed) · 2 unverified
calc_mean_opt_moments utils/helper.py ran MIT (permissive) · f1acb525c0929888 · report fixture: signature opt:Adam/0/? · returned dict · level recorded 2026-09-24
calc_rank utils/helper.py ran MIT (permissive) · 238266345b37c6dc · report fixture: signature name:str/0/str, z:Tensor/2/float · returned dict · level recorded 2026-09-24
evaluate in 514 papers utils/evaluate.py ran MIT (permissive) · 1d3835836ba9076b · report fixture: signature env:MockEnv/0/?, eval_policy_module:callable/0/?, max_episode_steps:int/0/int, action_repeat:int/0/int, video_env:MockVideoEnv/0/? · returned dict · level recorded 2026-09-24
flatten_batch utils/buffers.py ran MIT (permissive) · 5463329fd15b6ca9 · report fixture: signature batch:ReplayBufferSamples/1/TensorDict · returned ReplayBufferSamples · level recorded 2026-09-24
mlp in 108 papers utils/layers.py ran MIT (permissive) · 9acd81aa05192bdb · report fixture: signature in_dim:int/0/int, mlp_dims:list/1/int, out_dim:int/0/int, act_fn:callable/0/?, dropout:float/0/float · returned Sequential · level recorded 2026-09-25
symlog in 24 papers
census: 5 implementations from 7 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
utils/helper.py ran fingerprinted MIT (permissive) · 7fb5eb47c3b273d5 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-25
mlp_ensemble utils/layers.py unverified MIT (permissive) · 6c36e9ed51bed5c6 · report
to_nstep utils/buffers.py unverified MIT (permissive) · 9babf91705bd55e7 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model".

1 assembly on this paper: 0 harvested, 1 generated.

generated Assembly for DCWM (graph method: DCWM), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 0 ran · 1 unverified. Its end-to-end level was lowered from level 2 to level 0 on 2026-09-10 (level 0: no end-to-end run is now recorded); Syntology's graph records why: “lowered to the entry brick level: a single-routine assembly IS its brick”.

label matches by construction: the code was generated for this method (not judged by a model)

  1. fit_mean_weighted_elite entry · level 0 · unverified · 4227909746484858b8130f58051b97a49c0663dde1fba62d3b7909eb3ecf5931

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2503.00653") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Continuous ControlModel Predictive ControlReinforcement Learning (RL)continuous-control

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