Pith. sign in

REVIEW 6 cited by

Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrations

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 2303.01497 v1 pith:55MXVZSH submitted 2023-03-02 cs.RO cs.AIcs.CVcs.LG

classification cs.ROcs.AIcs.CVcs.LG
keywords demonstrationsfishimitationlearningrobotskillsacrossbase-policy
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

While imitation learning provides us with an efficient toolkit to train robots, learning skills that are robust to environment variations remains a significant challenge. Current approaches address this challenge by relying either on large amounts of demonstrations that span environment variations or on handcrafted reward functions that require state estimates. Both directions are not scalable to fast imitation. In this work, we present Fast Imitation of Skills from Humans (FISH), a new imitation learning approach that can learn robust visual skills with less than a minute of human demonstrations. Given a weak base-policy trained by offline imitation of demonstrations, FISH computes rewards that correspond to the "match" between the robot's behavior and the demonstrations. These rewards are then used to adaptively update a residual policy that adds on to the base-policy. Across all tasks, FISH requires at most twenty minutes of interactive learning to imitate demonstrations on object configurations that were not seen in the demonstrations. Importantly, FISH is constructed to be versatile, which allows it to be used across robot morphologies (e.g. xArm, Allegro, Stretch) and camera configurations (e.g. third-person, eye-in-hand). Our experimental evaluations on 9 different tasks show that FISH achieves an average success rate of 93%, which is around 3.8x higher than prior state-of-the-art methods.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

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

  1. OmniTacTune: Policy-Agnostic Real-World RL for Tactile Residual Adaptation of Visual Policies

    cs.RO 2026-07 conditional novelty 6.0 of 10

    A policy-agnostic two-stage real-world RL method learns tactile residual corrections on frozen visual policies, lifting contact-rich task success from 5–40% to 85–100% in under 80 minutes.

  2. CDP: Towards Robust Autoregressive Visuomotor Policy Learning via Causal Diffusion

    cs.CV 2025-06 conditional novelty 6.0 of 10

    Causal Diffusion Policy adds historical action conditioning and attention cache sharing to diffusion-based robot policies, improving success rates on most tested manipulation tasks under degraded observations.

  3. Residual Reward Models for Preference-based Reinforcement Learning

    cs.LG 2025-07 conditional novelty 5.0 of 10

    Combining a hand-designed or learned prior reward with a preference-trained residual improves sample efficiency and final performance in preference-based reinforcement learning.

  4. 3DFlowAction: Learning Cross-Embodiment Manipulation from 3D Flow World Model

    cs.RO 2025-06 conditional novelty 5.0 of 10

    A diffusion world model predicts 3D optical flow as an embodiment-agnostic action plan, and constrained optimization converts the flow into robot arm actions.

  5. Is Optimal Transport Necessary for Inverse Reinforcement Learning?

    cs.LG 2025-06 conditional novelty 4.0 of 10

    Simple nearest-neighbor and segment-matching reward functions match or beat Optimal Transport based Inverse RL across 32 benchmarks.

  6. Spatial-Temporal Aware Visuomotor Diffusion Policy Learning

    cs.RO 2025-07 conditional novelty 3.0 of 10

    A diffusion-based visuomotor policy gains 3D and 4D scene awareness from a dynamic Gaussian world model, improving simulated and real robot manipulation success rates.

Pith tools