Papers › Behavior Generation with Latent Actions

Behavior Generation with Latent Actions

5 Mar 2024arXiv:2403.03181archive 2025-07-28

Seungjae Lee, Yibin Wang, Haritheja Etukuru, H. Jin Kim, Nur Muhammad Mahi Shafiullah, Lerrel Pinto

Generative modeling of complex behaviors from labeled datasets has been a longstanding problem in decision making. Unlike language or image generation, decision making requires modeling actions - continuous-valued vectors that are multimodal in their distribution, potentially drawn from uncurated sources, where generation errors can compound in sequential prediction. A recent class of models called Behavior Transformers (BeT) addresses this by discretizing actions using k-means clustering to capture different modes. However, k-means struggles to scale for high-dimensional action spaces or long sequences, and lacks gradient information, and thus BeT suffers in modeling long-range actions. In this work, we present Vector-Quantized Behavior Transformer (VQ-BeT), a versatile model for behavior generation that handles multimodal action prediction, conditional generation, and partial observations. VQ-BeT augments BeT by tokenizing continuous actions with a hierarchical vector quantization module. Across seven environments including simulated manipulation, autonomous driving, and robotics, VQ-BeT improves on state-of-the-art models such as BeT and Diffusion Policies. Importantly, we demonstrate VQ-BeT's improved ability to capture behavior modes while accelerating inference speed 5x over Diffusion Policies. Videos and code can be found https://sjlee.cc/vq-bet

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="2403.03181")

Code

Syntology Ran 7 of 14 code samples harvested from 2 repositories linked to this paper; 7 have no recorded run. Of those that ran: 1 ran · honoured contract; 2 ran · violated contract; 1 ran · our draft was wrong; 3 ran with no contract checked.

By repository: official repository: 10 samples from 1 repository, 7 ran; community (archive-listed): 4 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.

jayLEE0301/vq_bet_official officialmentioned in paperpytorchMIT report
ziyadsheeba/qfat mentioned on GitHubApache-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

14 samples harvested; 7 ran; 1 honoured the contract we drafted; 7 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.

1ran · honoured contract
2ran · violated contract
1ran · our draft was wrong
3ran
7unverified

Licence: 0 of the 14 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 2 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.

default jayLEE0301/vq_bet_official/vector_quantize_pytorch/residual_vq.py official repository ran · violated contract fingerprinted MIT (permissive) · 60fff7c3c400d7ff · report
exists jayLEE0301/vq_bet_official/vector_quantize_pytorch/residual_vq.py official repository ran · violated contract MIT (permissive) · aa5486a3650902d8 · report
get_tensor jayLEE0301/vq_bet_official/vqvae/vqvae_utils.py official repository ran MIT (permissive) · 5f5f6bab7bdf48cb · report
identity jayLEE0301/vq_bet_official/vector_quantize_pytorch/vector_quantize_pytorch.py official repository ran · honoured contract fingerprinted MIT (permissive) · f3232418205f7cbd · report
new_gelu jayLEE0301/vq_bet_official/vq_behavior_transformer/gpt.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 92101b06ecbf1f1e · report
q_inv jayLEE0301/vq_bet_official/envs/antenv/ant.py official repository ran fingerprinted MIT (permissive) · b518b50864d18ead · report
round_up_multiple jayLEE0301/vq_bet_official/vector_quantize_pytorch/residual_vq.py official repository ran fingerprinted MIT (permissive) · bf63ff5f88b9f6b3 · report
create_gather_env jayLEE0301/vq_bet_official/envs/antenv/create_gather_env.py official repository unverified MIT (permissive) · cde2ae8e18dc91d3 · report
create_maze_env jayLEE0301/vq_bet_official/envs/antenv/create_maze_env.py official repository unverified MIT (permissive) · 45edef65d8e9ec47 · report
q_mult jayLEE0301/vq_bet_official/envs/antenv/ant.py official repository unverified MIT (permissive) · b5987afb2eb91889 · report
collate_policy ziyadsheeba/qfat/src/qfat/datasets/dataset.py community (archive-listed) unverified Apache-2.0 (permissive) · 290e63bdbac69bc8 · report
covariance_ellipse ziyadsheeba/qfat/src/qfat/utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 1a66725274da6033 · report
get_image_from_fig ziyadsheeba/qfat/src/qfat/utils.py community (archive-listed) unverified Apache-2.0 (permissive) · c32a6f9abdf33258 · report
load_metric_from_wandb ziyadsheeba/qfat/src/qfat/utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 512357de55b799f0 · report

Tasks

Autonomous DrivingDecision MakingImage GenerationImitation LearningQuantization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDiffusionDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSPEEDSoftmaxTransformerk-Means Clustering

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