Trendoday

ExRL: Sample-Efficient Online Adaptation of Long-Chunk Policies via Execution Length Control

Predicting long action chunks, often spanning dozens of timesteps, has become a key ingredient in increasingly capable robot policies. In this paper, we find that adapting these long-chunk policies wi

  • Upvotes4
–Rank now
#22Peak rank
1Days on list
62Score · 7d
Nov 11, 2026First seen
Rank · 7 days

About this paper

Execution at the Right Length (ExRL) enables sample-efficient adaptation of long-chunk robot policies by training a lightweight adapter to predict each chunk’s execution length using off-policy reinforcement learning.

Predicting long action chunks, often spanning dozens of timesteps, has become a key ingredient in increasingly capable robot policies. In this paper, we find that adapting these long-chunk policies with existing reinforcement learning (RL) methods can require many online samples due to the high dimensionality of the action chunks being optimized, making such adaptation impractical in real-world scenarios where interaction data are costly to collect. Our key insight is to shift adaptation from optimizing actions to optimizing how long to execute each predicted action chunk. This keeps the adaptation space low-dimensional while its expressivity grows with the chunk size. We thus introduce…

long action chunkslong-chunk policiesreinforcement learningoff-policy RL algorithmssample-efficient adaptationlightweight adapterexecution lengthbase policyhigh-dimensional action chunkslow-dimensional adaptation space
Upvotes
4
Authors
8
Published
Nov 10, 2026

Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.

Trending history

ExRL: Sample-Efficient Online Adaptation of Long-Chunk Policies via Execution Length Control was first seen on Hugging Face · Daily papers on Nov 11, 2026. Since then it has appeared in 8 checks on 1 different day. Its best position was #22 of 30, reached on Nov 11, 13:28 UTC. It dropped off the list after Nov 11, 19:28 UTC.

Rank history

Position on Hugging Face · Daily papers at every check (lower is better).

#1#11#20#30 05:2808:5812:2815:5819:28 Nov 11, 05:28 UTC · #23Nov 11, 07:28 UTC · #24Nov 11, 09:28 UTC · #25Nov 11, 11:28 UTC · #24Nov 11, 13:28 UTC · #22Nov 11, 15:28 UTC · #26Nov 11, 17:28 UTC · #27Nov 11, 19:28 UTC · #29

Last 14 days

Best rank per day (UTC).

Nov 3today

Metric history

Platform metric as reported by Hugging Face.

0134 05:2808:5812:2815:5819:28 Nov 11, 05:28 UTC · 4Nov 11, 07:28 UTC · 4Nov 11, 09:28 UTC · 4Nov 11, 11:28 UTC · 4Nov 11, 13:28 UTC · 4Nov 11, 15:28 UTC · 4Nov 11, 17:28 UTC · 4Nov 11, 19:28 UTC · 4

Questions

Is ExRL: Sample-Efficient Online Adaptation of Long-Chunk Policies via Execution Length Control trending on HF Daily Papers right now?

Not at the moment. It was last on the list on Nov 11, 19:28 UTC, after 1 day of trending.

What is the highest rank ExRL: Sample-Efficient Online Adaptation of Long-Chunk Policies via Execution Length Control reached?

#22 on Hugging Face · Daily papers, on Nov 11, 13:28 UTC. Trendoday checks this list every 120 minutes.

How long has ExRL: Sample-Efficient Online Adaptation of Long-Chunk Policies via Execution Length Control been trending?

It was first seen on Nov 11, 2026 and has been on the list on 1 day (8 checks) since.