arXiv AI June 2, 2026 By Fuyuan Qian, Menglong Zhang, Song Wang, Quanying Liu

Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta-Reinforcement Learning

arXiv:2606. 00780v1 Announce Type: cross Abstract: Offline meta-reinforcement learning leverages static datasets to enable agents to generalize to unseen environments by combining offline efficiency with meta-learning adaptability, yet it faces key challenges from context and policy distribution shifts.

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 AI.

arXiv Machine Learning

Sep 10

Temporal Consistency Improves Generalization in Contextual Offline Meta Reinforcement Learning

arXiv:2603.02935v2 Announce Type: replace Abstract: Offline meta-reinforcement learning seeks to learn a policy that generalizes to new related tasks online. Context-based methods infer a task repres...

By Mohammadreza Nakheai, Aidan Scannell, Kevin Luck, Joni Pajarinen

diffusion reinforcement-learning benchmarks

arXiv Machine Learning

Jun 25

Towards Scalable Multi-Task Reinforcement Learning with Large Decision Models

arXiv:2606. 24962v1 Announce Type: new Abstract: Recent progress in large-scale sequence modeling has shown that a single model can learn useful representations across highly diverse data distributions.

By Thibaut Kulak

llms agents reinforcement-learning robotics multimodal

arXiv AI

Sep 10

WorldAgen: Unified State-Action Prediction with Test-Time World Model Training

WorldAgen is a unified framework that jointly learns world modeling and action prediction using a shared Transformer backbone with two specialized heads. It introduces a Mixed Unidirectional Attention Mask to separate the world model and agent model, and enables Test-Time Training (TTT) by sampling exploratory actions and updating the world model with real state transitions. Experiments on CALVIN and LIBERO show that WorldAgen matches or surpasses state‑of‑the‑art methods, especially when TTT is applied to a few samples.

By Chi Wan, Kangrui Wang, Yuan Si, Pingyue Zhang, Manling Li

llms agents multimodal benchmarks

arXiv Machine Learning

Jul 22

Breaking Feedback-Blindness: Utility-Augmented Transformer for Sequential Decision Making

arXiv:2607. 18910v1 Announce Type: new Abstract: Sequential decision making in non-stationary and partially observable environments requires rapid adaptation to latent regime changes.

By Yuyang Shen, Shan Dai, Daimin Chen

llms benchmarks

arXiv Machine Learning

Jun 5

Training One Model to Master Cross-Level Agentic Actions via Reinforcement Learning

arXiv:2512. 09706v2 Announce Type: replace Abstract: The paradigm of agentic AI is shifting from engineered complex workflows to post-training native models.

By Kaichen He, Zihao Wang, Muyao Li, Anji Liu, Yitao Liang

agents reinforcement-learning robotics fine-tuning benchmarks

arXiv Machine Learning

Jun 16

Efficient Reinforcement Learning by Guiding World Models with Non-Curated Data

arXiv:2502. 19544v3 Announce Type: replace Abstract: Leveraging offline data is a promising way to improve the sample efficiency of online reinforcement learning (RL).

By Yi Zhao, Aidan Scannell, Wenshuai Zhao, Yuxin Hou, Tianyu Cui, Le Chen, Dieter B\"uchler, Arno Solin, Juho Kannala, Joni Pajarinen

reinforcement-learning robotics fine-tuning

One email a morning, machine-written

Related stories

Temporal Consistency Improves Generalization in Contextual Offline Meta Reinforcement Learning

Towards Scalable Multi-Task Reinforcement Learning with Large Decision Models

WorldAgen: Unified State-Action Prediction with Test-Time World Model Training

Breaking Feedback-Blindness: Utility-Augmented Transformer for Sequential Decision Making

Training One Model to Master Cross-Level Agentic Actions via Reinforcement Learning

Efficient Reinforcement Learning by Guiding World Models with Non-Curated Data