arXiv Machine Learning June 25, 2026 By Kathryn Wantlin, Chongyi Zheng, Benjamin Eysenbach

Consistent Zero-Shot Imitation with Contrastive Goal Inference

Read the original on arXiv Machine Learning →

arXiv:2510. 17059v2 Announce Type: replace Abstract: Zero-shot imitation learning requires an agent to reproduce expert behavior from a single demonstration without additional environment interaction or gradient updates at test time.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 21

Generalize and Guide: Decomposing Rewards for Few-Shot Inverse Reinforcement Learning

arXiv:2607. 17760v1 Announce Type: cross Abstract: Inverse reinforcement learning (IRL) provides a powerful framework for learning from demonstrations.

By Ziyi Liu, Grace Zhang

agents reinforcement-learning robotics

arXiv AI

Aug 7

Autonomous Learning From Success and Failure: Goal-Conditioned Supervised Learning with Negative Feedback

arXiv:2509. 03206v2 Announce Type: replace-cross Abstract: Learning from reward functions and imitation learning of demonstrations are the two principal approaches for training autonomous systems that interact with an environment through action and observation.

By Zeqiang Zhang, Fabian Wurzberger, Gerrit Schmid, Sebastian Gottwald, Daniel A. Braun

agents

Hugging Face Trending Papers

Jul 20

Generalize and Guide: Decomposing Rewards for Few-Shot Inverse Reinforcement Learning

Inverse reinforcement learning (IRL) provides a powerful framework for learning from demonstrations. However, real-world tasks often exhibit substantial natural variations (e.

agents reinforcement-learning robotics

arXiv AI

Jul 7

Rational Inverse Reasoning: Few-Shot Imitation by Inferring Intent through Planning

arXiv:2508. 08983v2 Announce Type: replace-cross Abstract: Humans can learn a new manipulation task from one or two demonstrations and then perform it in a new room, with new objects, under new constraints.

By Ben Zandonati, Tom\'as Lozano-P\'erez, Leslie Pack Kaelbling

llms robotics multimodal benchmarks

arXiv Machine Learning

Jun 2

Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards

arXiv:2606. 02194v1 Announce Type: new Abstract: Distilling expert demonstration data into large generative models using behavioral cloning is a scalable approach to learning capable policies for robotic control, particularly for dexterous manipulation.

By Christian Scherer, Joe Watson, Theo Gruner, Daniel Palenicek, Ingmar Posner, Jan Peters

reinforcement-learning robotics fine-tuning

arXiv Machine Learning

Sep 1

Locally-Guided Actor-Critic: Training a Goal-conditioned Actor with a Subgoal-aware Critic

arXiv:2608.30406v1 Announce Type: new Abstract: Goal-conditioned reinforcement learning struggles with long horizons when rewards are sparse. While a planner can provide subgoals to guide a low-level...

By Olivier Serris, St\'ephane Doncieux, Olivier Sigaud

agents reinforcement-learning

One email a morning, machine-written

Related stories

Generalize and Guide: Decomposing Rewards for Few-Shot Inverse Reinforcement Learning

Autonomous Learning From Success and Failure: Goal-Conditioned Supervised Learning with Negative Feedback

Generalize and Guide: Decomposing Rewards for Few-Shot Inverse Reinforcement Learning

Rational Inverse Reasoning: Few-Shot Imitation by Inferring Intent through Planning

Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards

Locally-Guided Actor-Critic: Training a Goal-conditioned Actor with a Subgoal-aware Critic