Pith. sign in

REVIEW 1 cited by

Distance Weighted Supervised Learning for Offline Interaction Data

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 2304.13774 v1 pith:IOO22SVX submitted 2023-04-26 cs.LG

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

Sequential decision making algorithms often struggle to leverage different sources of unstructured offline interaction data. Imitation learning (IL) methods based on supervised learning are robust, but require optimal demonstrations, which are hard to collect. Offline goal-conditioned reinforcement learning (RL) algorithms promise to learn from sub-optimal data, but face optimization challenges especially with high-dimensional data. To bridge the gap between IL and RL, we introduce Distance Weighted Supervised Learning or DWSL, a supervised method for learning goal-conditioned policies from offline data. DWSL models the entire distribution of time-steps between states in offline data with only supervised learning, and uses this distribution to approximate shortest path distances. To extract a policy, we weight actions by their reduction in distance estimates. Theoretically, DWSL converges to an optimal policy constrained to the data distribution, an attractive property for offline learning, without any bootstrapping. Across all datasets we test, DWSL empirically maintains behavior cloning as a lower bound while still exhibiting policy improvement. In high-dimensional image domains, DWSL surpasses the performance of both prior goal-conditioned IL and RL algorithms. Visualizations and code can be found at https://sites.google.com/view/dwsl/home .

Discussion (0). Continue with ORCID 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. Closing the Gap between TD Learning and Supervised Learning with $Q$-Conditioned Maximization

    cs.LG 2025-06 conditional novelty 5.0 of 10

    GCReinSL adds Q-conditioned maximization to supervised offline RL, using normalizing flows to estimate goal-reaching probabilities and expectile regression to condition actions on the best in-distribution value, impro...

Pith tools