arXiv AI July 7, 2026 By Andrea Fraschini, Davide Tenedini, Riccardo Zamboni, Mirco Mutti, Marcello Restelli

Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching

arXiv:2603. 27044v3 Announce Type: replace-cross Abstract: Deep Reinforcement Learning (DRL) is widely recognized as sample-inefficient, a limitation attributable in part to the high dimensionality and substantial functional redundancy inherent to the policy parameter space.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv Machine Learning

Jul 3

On the Sample Efficiency of Inverse Dynamics Models for Semi-Supervised Imitation Learning

arXiv:2602. 02762v2 Announce Type: replace Abstract: Semi-supervised imitation learning (SSIL) consists in learning a policy from a small dataset of action-labeled trajectories and a much larger dataset of action-free trajectories.

By Sacha Morin, Moonsub Byeon, Alexia Jolicoeur-Martineau, S\'ebastien Lachapelle

benchmarks

arXiv AI

Jun 11

Implicit Neural Representations of Individual Behavior

arXiv:2606. 12200v1 Announce Type: cross Abstract: We study policy representation learning from unlabeled multi-policy behavioral data.

By Andrew Kang, Priya Narasimhan

agents robotics

arXiv Machine Learning

Jun 9

Latent Spherical Flow Policy for Reinforcement Learning with Combinatorial Actions

arXiv:2601. 22211v2 Announce Type: replace Abstract: Reinforcement learning (RL) with combinatorial action spaces remains challenging because feasible action sets are exponentially large and governed by complex feasibility constraints, making direct policy parameterization impractical.

By Lingkai Kong, Anagha Satish, Hezi Jiang, Akseli Kangaslahti, Andrew Ma, Wenbo Chen, Mingxiao Song, Lily Xu, Milind Tambe

diffusion reinforcement-learning benchmarks

arXiv AI

Jun 4

Unifying Model-Free Efficiency and Model-Based Representations via Latent Dynamics

arXiv:2602. 12643v2 Announce Type: replace-cross Abstract: We present Unified Latent Dynamics (ULD), a novel reinforcement learning algorithm that unifies the efficiency of model-free methods with the representational strengths of model-based approaches, without incurring planning overhead.

By Jashaswimalya Acharjee, Balaraman Ravindran

rag diffusion reinforcement-learning robotics

arXiv Machine Learning

Jun 26

Reinforcement Fine-Tuning of Flow-Matching Policies for Vision-Language-Action Models

arXiv:2510. 09976v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models such as OpenVLA, Octo, and $\pi_0$ have shown strong generalization by leveraging large-scale demonstrations, yet their performance is still fundamentally constrained by the quality and coverage of supervised data.

By Mingyang Lyu, Yinqian Sun, Erliang Lin, Huangrui Li, Ruolin Chen, Feifei Zhao, Yi Zeng

diffusion reinforcement-learning fine-tuning multimodal benchmarks

arXiv Machine Learning

Jun 25

ACT-JEPA: Novel Joint-Embedding Predictive Architecture for Efficient Policy Representation Learning

arXiv:2501. 14622v5 Announce Type: replace Abstract: Learning efficient representations for decision-making policies is a challenge in imitation learning (IL).

By Aleksandar Vujinovic, Aleksandar Kovacevic

rag diffusion

Related stories

On the Sample Efficiency of Inverse Dynamics Models for Semi-Supervised Imitation Learning

Implicit Neural Representations of Individual Behavior

Latent Spherical Flow Policy for Reinforcement Learning with Combinatorial Actions

Unifying Model-Free Efficiency and Model-Based Representations via Latent Dynamics

Reinforcement Fine-Tuning of Flow-Matching Policies for Vision-Language-Action Models

ACT-JEPA: Novel Joint-Embedding Predictive Architecture for Efficient Policy Representation Learning