Pith. sign in

REVIEW 1 cited by

Dynamical Distance Learning for Semi-Supervised and Unsupervised Skill Discovery

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 1907.08225 v4 pith:TAKSR6JG submitted 2019-07-18 cs.LG cs.AIcs.CVcs.ROstat.ML

classification cs.LGcs.AIcs.CVcs.ROstat.ML
keywords dynamicallearnrewarddistancesfunctiongoaltaskused
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Reinforcement learning requires manual specification of a reward function to learn a task. While in principle this reward function only needs to specify the task goal, in practice reinforcement learning can be very time-consuming or even infeasible unless the reward function is shaped so as to provide a smooth gradient towards a successful outcome. This shaping is difficult to specify by hand, particularly when the task is learned from raw observations, such as images. In this paper, we study how we can automatically learn dynamical distances: a measure of the expected number of time steps to reach a given goal state from any other state. These dynamical distances can be used to provide well-shaped reward functions for reaching new goals, making it possible to learn complex tasks efficiently. We show that dynamical distances can be used in a semi-supervised regime, where unsupervised interaction with the environment is used to learn the dynamical distances, while a small amount of preference supervision is used to determine the task goal, without any manually engineered reward function or goal examples. We evaluate our method both on a real-world robot and in simulation. We show that our method can learn to turn a valve with a real-world 9-DoF hand, using raw image observations and just ten preference labels, without any other supervision. Videos of the learned skills can be found on the project website: https://sites.google.com/view/dynamical-distance-learning.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

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

  1. FOUNDER: Grounding Foundation Models in World Models for Open-Ended Embodied Decision Making

    cs.RO 2025-07 conditional novelty 6.0 of 10

    FOUNDER maps foundation-model embeddings of text or video prompts into world-model goal states and rewards policies by predicted temporal distance to those goals, improving reward-free multi-task offline control.

Pith tools