Pith. sign in

REVIEW 26 cited by

Steering Your Generalists: Improving Robotic Foundation Models via Value Guidance

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 2410.13816 v2 pith:OAXHWHKX submitted 2024-10-17 cs.RO cs.LG

Steering Your Generalists: Improving Robotic Foundation Models via Value Guidance

classification cs.RO cs.LG
keywords policiesdifferentperformancerobotictrainedvalueapproachdata
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Large, general-purpose robotic policies trained on diverse demonstration datasets have been shown to be remarkably effective both for controlling a variety of robots in a range of different scenes, and for acquiring broad repertoires of manipulation skills. However, the data that such policies are trained on is generally of mixed quality -- not only are human-collected demonstrations unlikely to perform the task perfectly, but the larger the dataset is, the harder it is to curate only the highest quality examples. It also remains unclear how optimal data from one embodiment is for training on another embodiment. In this paper, we present a general and broadly applicable approach that enhances the performance of such generalist robot policies at deployment time by re-ranking their actions according to a value function learned via offline RL. This approach, which we call Value-Guided Policy Steering (V-GPS), is compatible with a wide range of different generalist policies, without needing to fine-tune or even access the weights of the policy. We show that the same value function can improve the performance of five different state-of-the-art policies with different architectures, even though they were trained on distinct datasets, attaining consistent performance improvement on multiple robotic platforms across a total of 12 tasks. Code and videos can be found at: https://nakamotoo.github.io/V-GPS

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 26 Pith papers

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

  1. Adapting Generalist Robot Policies with Semantic Reinforcement Learning

    cs.RO 2026-06 unverdicted novelty 7.0

    SARL optimizes language prompt inputs to generalist vision-language-action policies through online RL to solve complex long-horizon tasks by composing existing skills.

  2. Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning

    cs.LG 2026-06 unverdicted novelty 7.0

    QGF performs test-time policy optimization for flow models in RL by guiding a behavior-cloned reference policy with value-function gradients, achieving strong results on high-dimensional offline RL benchmarks without ...

  3. BOKBO (Best of K Bad Options): Calibrated Abstention for VLA Policies

    cs.LG 2026-05 unverdicted novelty 7.0

    BOKBO is the first conformal abstention method for K-sample VLA policies that supplies finite-sample distribution-free guarantees on executed violation rates, with global and Mondrian per-task variants.

  4. Offline Policy Evaluation for Manipulation Policies via Discounted Liveness Formulation

    cs.RO 2026-05 conditional novelty 7.0

    A liveness-based Bellman operator enables conservative offline policy evaluation for manipulation tasks by encoding task progression and reducing truncation bias from finite horizons.

  5. Agent-Centric Observation Adaptation for Robust Visual Control under Dynamic Perturbations

    cs.RO 2026-04 unverdicted novelty 7.0

    ACO-MoE employs agent-centric mixture-of-experts to decouple task-relevant features from dynamic visual perturbations in RL, recovering 95.3% of clean performance on the new VDCS benchmark.

  6. Agent-Centric Observation Adaptation for Robust Visual Control under Dynamic Perturbations

    cs.RO 2026-04 unverdicted novelty 7.0

    ACO-MoE recovers 95.3% of clean-input performance in visual control tasks under Markov-switching corruptions by routing restoration experts and anchoring representations to clean foreground masks.

  7. Action Images: End-to-End Policy Learning via Multiview Video Generation

    cs.CV 2026-04 unverdicted novelty 7.0

    Action Images turn robot arm motions into interpretable multiview pixel videos, letting video backbones serve as zero-shot policies for end-to-end robot learning.

  8. World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry

    cs.LG 2026-04 accept novelty 7.0

    WAV self-improves action-conditioned world models by cycle-consistent verification of state plausibility and sparse action reachability, doubling sample efficiency and lifting policy reward by over 22% on nine tasks.

  9. You've Got a Golden Ticket: Improving Generative Robot Policies With A Single Noise Vector

    cs.RO 2026-03 conditional novelty 7.0

    Optimizing a single constant initial noise vector for frozen generative robot policies improves success rates on 38 of 43 tasks by up to 58% relative improvement.

  10. Steering Your Diffusion Policy with Latent Space Reinforcement Learning

    cs.RO 2025-06 unverdicted novelty 7.0

    DSRL steers pretrained diffusion policies for robotics by applying RL to their latent noise inputs, achieving sample-efficient real-world adaptation with only black-box access.

  11. SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning

    cs.RO 2026-03 conditional novelty 6.5

    A video-language model with per-timestep spatiotemporal CoT and dense progress prediction can serve as the sole reward for zero-shot online robot RL on 24 unseen manipulation tasks.

  12. DREAMSTEER: Latent World Models Can Steer VLA Policies During Deployment Without Any Finetuning

    cs.RO 2026-07 conditional novelty 6.0

    A frozen VLA plus latent world-model rollouts and a value model can raise real-robot OOD manipulation success from 23.75% to 66.25% without any target-environment finetuning.

  13. Trust Your Instincts: Confidence-Driven Test-Time RL for Vision-Language-Action Models

    cs.RO 2026-06 unverdicted novelty 6.0

    T^2VLA is a test-time reinforcement learning framework for VLAs that uses internal confidence to define intrinsic rewards via similarity to high-confidence expert demonstrations and a dual-expert bootstrapping mechanism.

  14. Inference-Time Robot Behavior Steering through Physically-Aware Reconfiguration of Task-Structure

    cs.RO 2026-06 unverdicted novelty 6.0

    ReStruct steers robot policies at inference time by reconfiguring task structure with neural automata and synchronous products, claiming up to 25% gains over VLA models in success and preference adherence.

  15. Learning Process Rewards via Success Visitation Matching for Efficient RL

    cs.LG 2026-06 unverdicted novelty 6.0

    Success Visitation Matching uses a discriminator to turn sparse outcome rewards into dense process rewards by matching visitations of successful episodes, provably preserving the optimal policy and speeding up robotic...

  16. Robot Critics that Sweat the Small Stuff

    cs.RO 2026-06 unverdicted novelty 6.0

    Fine-tuning VLMs with pairwise progress supervision from policy rollouts improves fine-grained failure detection and boosts robot manipulation success by 11% real-world and 5.9% in simulation.

  17. VeriSpace: Spatially Grounded Action Verification for Vision-Language-Action Models

    cs.RO 2026-06 unverdicted novelty 6.0

    VeriSpace is a 3D-aware action verifier that improves test-time action selection in VLA models by encoding scenes with visual and geometric information and reasoning over spatial relations and goal progress.

  18. VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model

    cs.RO 2026-05 unverdicted novelty 6.0

    VLA-ATTC equips VLA models with adaptive test-time compute via an uncertainty clutch and relative action critic, cutting failure rates by over 50% on LIBERO-LONG.

  19. Breaking Lock-In: Preserving Steerability under Low-Data VLA Post-Training

    cs.RO 2026-04 unverdicted novelty 6.0

    DeLock mitigates lock-in in low-data VLA post-training via visual grounding preservation and test-time contrastive prompt guidance, outperforming baselines across eight evaluations while matching data-heavy generalist...

  20. FASTER: Value-Guided Sampling for Fast RL

    cs.LG 2026-04 unverdicted novelty 6.0

    FASTER models multi-candidate denoising as an MDP and trains a value function to filter actions early, delivering the performance of full sampling at lower cost in diffusion RL policies.

  21. Sumo: Dynamic and Generalizable Whole-Body Loco-Manipulation

    cs.RO 2026-04 unverdicted novelty 6.0

    Test-time steering of pre-trained whole-body policies via sample-based planning lets legged robots generalize dynamic loco-manipulation to varied heavy objects and tasks without additional training or tuning.

  22. You've Got a Golden Ticket: Improving Generative Robot Policies With A Single Noise Vector

    cs.RO 2026-03 unverdicted novelty 6.0

    A single constant initial noise vector found by Monte-Carlo search improves frozen diffusion and flow-matching robot policies on 46 of 51 tasks, by up to 55% absolute success rate.

  23. LLM-as-a-Verifier: A General-Purpose Verification Framework

    cs.AI 2026-07 conditional novelty 5.0

    Expecting over scoring-token logits yields continuous, scalable verification that improves agent trajectory selection and dense RL rewards across coding, robotics, and medical benchmarks.

  24. LLM-as-a-Verifier: A General-Purpose Verification Framework

    cs.AI 2026-07 conditional novelty 5.0

    Computing the expectation over scoring-token logits instead of taking argmax enables verification to scale along granularity, repetition, and criteria decomposition, achieving state-of-the-art on four agentic benchmar...

  25. HiL-ResRL: A Model-Agnostic Finetuning Adapter via Human-in-the-loop Residual Reinforcement Learning

    cs.RO 2026-06 unverdicted novelty 5.0

    HiL-ResRL trains a model-agnostic residual policy on VLA actions using human-guided online RL, achieving over 95% success rate after 1.5 hours of real-robot training.

  26. DF-ExpEnse: Diffusion Filtered Exploration for Sample Efficient Finetuning

    cs.RO 2026-06 unverdicted novelty 5.0

    DF-ExpEnse improves sample efficiency in finetuning diffusion-based robotic policies by filtering diffusion-generated actions with critic ensembles and enabling fleet-level collaboration.