arXiv:2503. 03660v4 Announce Type: replace Abstract: We introduce a sequence-conditioned critic for Soft Actor-Critic (SAC) that models trajectory context with a lightweight Transformer and trains on aggregated $N$-step targets.
By Dong Tian, Onur Celik, Gerhard Neumann
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.
By Fuyuan Qian, Menglong Zhang, Song Wang, Quanying Liu
arXiv:2606. 04492v1 Announce Type: new Abstract: Cooperative Multi-Agent Reinforcement Learning (MARL) frequently suffers from severe reward sparsity and exploration bottlenecks.
By Zicheng Zhao, Yu Lan, Chengzhengxu Li, Zhaohan Zhang, Xiaoming Liu
The paper introduces Decision Titan, a variant of the Decision Transformer that incorporates Test‑Time Training (TTT) layers to store episodic memories in network parameters. It evaluates this architecture on the X‑Maze environment, showing that Decision Titan can learn long‑term dependencies up to 20 times longer than its context window and generalise to sequences 1.7 times longer than the training data. The study also finds that temporal generalisation depends on the choice of time embeddings and that the ability to learn long‑term dependencies hinges on how relevant information is encoded.
By Jude Waide, Robert Lieck
arXiv:2604. 01577v3 Announce Type: replace-cross Abstract: We study out of distribution generalization in streaming tasks where models are trained on short sequences but must operate over much longer, unknown horizons under bounded memory.
By Shota Takashiro, Masanori Koyama, Takeru Miyato, Yusuke Iwasawa, Yutaka Matsuo, Kohei Hayashi
MetaSteer is a new method for steering large language models that learns nonlinear, context-dependent interventions applied to attention projection matrices. Unlike traditional linear, context-independent techniques, MetaSteer adapts its effects based on the input, requiring no linear concept-geometry assumption. Trained once on a pooled preference corpus, it transfers zero‑shot to unseen concepts and out‑of‑distribution contexts, matching or surpassing strong task‑specific baselines on multiple benchmarks and model families.
By Mehdi Jafari, Hao Xue, Flora Salim