pith. machine review for the scientific record. sign in

arxiv: 1802.09484 · v1 · submitted 2018-02-26 · 📊 stat.ML · cs.LG

Recognition: unknown

Disentangling the independently controllable factors of variation by interacting with the world

Authors on Pith no claims yet
classification 📊 stat.ML cs.LG
keywords factorsenvironmentcontrollableindependentlyaspectschangesfeaturepolicy
0
0 comments X
read the original abstract

It has been postulated that a good representation is one that disentangles the underlying explanatory factors of variation. However, it remains an open question what kind of training framework could potentially achieve that. Whereas most previous work focuses on the static setting (e.g., with images), we postulate that some of the causal factors could be discovered if the learner is allowed to interact with its environment. The agent can experiment with different actions and observe their effects. More specifically, we hypothesize that some of these factors correspond to aspects of the environment which are independently controllable, i.e., that there exists a policy and a learnable feature for each such aspect of the environment, such that this policy can yield changes in that feature with minimal changes to other features that explain the statistical variations in the observed data. We propose a specific objective function to find such factors, and verify experimentally that it can indeed disentangle independently controllable aspects of the environment without any extrinsic reward signal.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Millimeter dust continuum and polarization in protoplanetary disks with scattering: A slab model

    astro-ph.EP 2026-05 conditional novelty 7.0

    Common analytic approximations underestimate protoplanetary disk millimeter continuum emission by 10-15%, causing overestimates of optical depth, mass, and temperature in SED analyses.

  2. Tidal pre-conditioning and ram-pressure stripping in NGC 1427A. Deep VLT/MUSE spectroscopy and FUV-to-radio observations trace a Fornax Cluster dwarf in transformation

    astro-ph.GA 2026-05 unverdicted novelty 6.0

    Multi-phase observations of NGC 1427A indicate tidal torquing from a dwarf fly-by has pre-conditioned its gas for ram-pressure stripping by the Fornax intracluster medium, placing the galaxy at the onset of environmen...

  3. The emerging timescale of young star clusters regulated by cluster stellar mass

    astro-ph.GA 2026-03 unverdicted novelty 6.0

    Massive young star clusters clear their natal gas faster than lower-mass clusters, based on HST and JWST imaging of four galaxies.

  4. Tidal pre-conditioning and ram-pressure stripping in NGC 1427A. Deep VLT/MUSE spectroscopy and FUV-to-radio observations trace a Fornax Cluster dwarf in transformation

    astro-ph.GA 2026-05 unverdicted novelty 4.0

    NGC 1427A exhibits ram-pressure stripping that has reached its ISM after tidal torquing by a nearby dwarf, marking the onset of cluster-driven gas loss and declining star formation.