Pith. sign in

REVIEW 2 cited by

Planning from Pixels using Inverse Dynamics Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2012.02419 v1 pith:3GNARAWO submitted 2020-12-04 cs.LG cs.AI

classification cs.LGcs.AI
keywords modelsdynamicschallengingcompletionlearningplanningactionsadaptively
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Learning task-agnostic dynamics models in high-dimensional observation spaces can be challenging for model-based RL agents. We propose a novel way to learn latent world models by learning to predict sequences of future actions conditioned on task completion. These task-conditioned models adaptively focus modeling capacity on task-relevant dynamics, while simultaneously serving as an effective heuristic for planning with sparse rewards. We evaluate our method on challenging visual goal completion tasks and show a substantial increase in performance compared to prior model-free approaches.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models

    cs.RO 2026-07 conditional novelty 6.0 of 10

    INTACT couples a one-step physical intent and a stop-gradient goal displacement through one shared action predictor, producing a search-free direct policy that reaches 95.33% macro success with zero candidates on the ...

  2. MGDA: Model-based Goal Data Augmentation for Offline Goal-conditioned Weighted Supervised Learning

    cs.LG 2024-12 conditional novelty 5.0 of 10

    A model-based goal augmentation method, MGDA, improves the stitching ability of offline goal-conditioned weighted supervised learning on maze benchmarks by filtering augmented goals through a locally Lipschitz dynamics model.

Pith tools