REVIEW 4 cited by
Inference-Time Policy Steering through Human Interactions
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
read the original abstract
Generative policies trained with human demonstrations can autonomously accomplish multimodal, long-horizon tasks. However, during inference, humans are often removed from the policy execution loop, limiting the ability to guide a pre-trained policy towards a specific sub-goal or trajectory shape among multiple predictions. Naive human intervention may inadvertently exacerbate distribution shift, leading to constraint violations or execution failures. To better align policy output with human intent without inducing out-of-distribution errors, we propose an Inference-Time Policy Steering (ITPS) framework that leverages human interactions to bias the generative sampling process, rather than fine-tuning the policy on interaction data. We evaluate ITPS across three simulated and real-world benchmarks, testing three forms of human interaction and associated alignment distance metrics. Among six sampling strategies, our proposed stochastic sampling with diffusion policy achieves the best trade-off between alignment and distribution shift. Videos are available at https://yanweiw.github.io/itps/.
Forward citations
Cited by 4 Pith papers
-
Learn from What We HAVE: History-Aware VErifier that Reasons about Past Interactions Online
A history-aware verifier that scores candidate actions using past interactions cuts failure rates in ambiguous robot manipulation tasks compared to using the generator alone.
-
Latent Policy Barrier: Learning Robust Visuomotor Policies by Staying In-Distribution
Latent Policy Barrier improves behavior-cloned visuomotor policies by using a latent dynamics model trained on expert and rollout data to guide actions back toward in-distribution expert states.
-
Adapting by Analogy: OOD Generalization of Visuomotor Policies via Functional Correspondence
A test-time method uses expert-provided functional correspondences to map out-of-distribution scenes to similar training scenes, letting a visuomotor policy reuse old behaviors without retraining.
-
Steering Robots with Inference-Time Interactions
Frozen imitation policies can be steered at inference time via user interactions, with a diffusion-sampling method and a constraint-enforcing framework that provides formal task guarantees.
Discussion (0). Sign in to comment.