Skip to content
AI News HubLIVE
Original source2 min read

HiRE: Hindsight Reward Editing for Policy Finetuning

Summary

arXiv:2609.27068v1 Announce Type: new Abstract: Pre-trained robot policies always require finetuning to adapt to specific environments. Reinforcement Learning (RL) offers high performance potential because it improves action optimality rather than simply mimicking data. However, such potential depends heavily on reward quality. Sparse rewards lack process feedback, human-designed rewards are costly and biased, and semantic rewards from foundation representations are often not control-centric. We propose Hindsight Reward Editing (HiRE), a training-free framework to break this reward bottleneck. HiRE bridges the broad knowledge of foundation representation models with physical control awareness, by contrasting successful and failed trajectories in hindsight. It calibrates foundation represe…

SourcearXiv RoboticsAuthor: Haoyi Niu, Zhengtao Han, Yufeng Ji, Zhongyu Li, Koushil Sreenath
HiRE: Hindsight Reward Editing for Policy Finetuning
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 22 Sep 2026]

Title:HiRE: Hindsight Reward Editing for Policy Finetuning

View a PDF of the paper titled HiRE: Hindsight Reward Editing for Policy Finetuning, by Haoyi Niu and 4 other authors

View PDF HTML (experimental)

Abstract:Pre-trained robot policies always require finetuning to adapt to specific environments. Reinforcement Learning (RL) offers high performance potential because it improves action optimality rather than simply mimicking data. However, such potential depends heavily on reward quality. Sparse rewards lack process feedback, human-designed rewards are costly and biased, and semantic rewards from foundation representations are often not control-centric. We propose Hindsight Reward Editing (HiRE), a training-free framework to break this reward bottleneck. HiRE bridges the broad knowledge of foundation representation models with physical control awareness, by contrasting successful and failed trajectories in hindsight. It calibrates foundation representation models by identifying "trap states" that are predicted as high-rewarding states yet eventually result in failure, and vice versa. HiRE explicitly penalizes these traps while boosting rewards for critical successful states. This approach can be flexibly compatible with any foundation representations and RL algorithms. Experiments show that HiRE consistently outperforms other reward recipes by delivering dense, control-aware feedback that prevents value function collapse and reward hacking, thereby achieving superior sample efficiency, stable policy updates, and higher performance ceilings, e.g., at least 3x performance of the base policies. Qualitative results are at this https URL .

Comments: CoRL 2026

Subjects:

Robotics (cs.RO)

Cite as: arXiv:2609.27068 [cs.RO]

(or arXiv:2609.27068v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2609.27068

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Haoyi Niu [view email] [v1] Tue, 22 Sep 2026 21:04:10 UTC (5,662 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled HiRE: Hindsight Reward Editing for Policy Finetuning, by Haoyi Niu and 4 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.RO

new | recent | 2026-09

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
  • arXiv:2609.27068v1 Announce Type: new Abstract: Pre-trained robot policies always require finetuning to adapt to specific environments. Reinforcement Learning (RL) offers high per…

Highlights and analysis are generated automatically and may contain errors. Check the original source.