Papers › Discovering Object-Centric Generalized Value Functions From Pixels

Discovering Object-Centric Generalized Value Functions From Pixels

27 Apr 2023arXiv:2304.13892archive 2025-07-28

Somjit Nath, Gopeshh Raaj Subbaraj, Khimya Khetarpal, Samira Ebrahimi Kahou

Deep Reinforcement Learning has shown significant progress in extracting useful representations from high-dimensional inputs albeit using hand-crafted auxiliary tasks and pseudo rewards. Automatically learning such representations in an object-centric manner geared towards control and fast adaptation remains an open research problem. In this paper, we introduce a method that tries to discover meaningful features from objects, translating them to temporally coherent "question" functions and leveraging the subsequent learned general value functions for control. We compare our approach with state-of-the-art techniques alongside other ablations and show competitive performance in both stationary and non-stationary settings. Finally, we also investigate the discovered general value functions and through qualitative analysis show that the learned representations are not only interpretable but also, centered around objects that are invariant to changes across tasks facilitating fast adaptation.

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="2304.13892")

Code

Syntology Ran 4 of 18 code samples harvested from 1 repository linked to this paper; 14 have no recorded run. Of those that ran: 3 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: official repository: 18 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

somjit77/oc_gvfs officialmentioned in papermentioned 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

18 samples harvested; 4 ran; 0 honoured the contract we drafted; 14 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.

3ran · our draft was wrong
1ran · fixture could not drive it
14unverified

Licence: 0 of the 18 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 somjit77/oc_gvfs. “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.

build_grid somjit77/oc_gvfs/slot_attention/model_jax.py official repository ran · our draft was wrong MIT (permissive) · d42ce6eadbd4a112 · report
spatial_broadcast somjit77/oc_gvfs/slot_attention/model_jax.py official repository ran · our draft was wrong MIT (permissive) · 85d66ddd34119a7c · report
spatial_flatten somjit77/oc_gvfs/slot_attention/model_jax.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · ca839bba3cb3de30 · report
unstack_and_split somjit77/oc_gvfs/slot_attention/model_jax.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · e48ab0090f3934eb · report
SlotAttention somjit77/oc_gvfs/slot_attention/model_jax.py official repository unverified MIT (permissive) · 2f149edc4ef4e955 · report
SlotAttentionAutoEncoder somjit77/oc_gvfs/slot_attention/model_jax.py official repository unverified MIT (permissive) · af260099be8d330b · report
SoftPositionEmbed somjit77/oc_gvfs/slot_attention/model_jax.py official repository unverified MIT (permissive) · 9d993e405d2762ce · report
build_network Somjit77/oc_gvfs/agent.py official repository unverified MIT (permissive) · 4f1d87d8590a8749 · report
build_question_network Somjit77/oc_gvfs/agent.py official repository unverified MIT (permissive) · 4eca72bd8d6a28b0 · report
get_cumulants Somjit77/oc_gvfs/utils.py official repository unverified MIT (permissive) · 870f819ffac4dd2c · report
newest Somjit77/oc_gvfs/plot_curves.py official repository unverified MIT (permissive) · c2586f375dd0aef5 · report
newest Somjit77/oc_gvfs/slot_attention/sa_utils.py official repository unverified MIT (permissive) · bd938d576acc121a · report
pre_process_batch Somjit77/oc_gvfs/slot_attention/sa_utils.py official repository unverified MIT (permissive) · c73955955ab59b07 · report
renormalize Somjit77/oc_gvfs/slot_attention/sa_utils.py official repository unverified MIT (permissive) · 58e7e6adb605babe · report
running_mean Somjit77/oc_gvfs/plot_curves.py official repository unverified MIT (permissive) · 85a38e4dd9181aaf · report
td_error Somjit77/oc_gvfs/utils.py official repository unverified MIT (permissive) · 5daf1e1813a04ece · report
td_error_state Somjit77/oc_gvfs/utils.py official repository unverified MIT (permissive) · 5dcbe772a2a9f6b7 · report
tolerant_mean Somjit77/oc_gvfs/plot_curves.py official repository unverified MIT (permissive) · a52c31e8052f488b · report

Tasks

Deep Reinforcement LearningObject

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