English
Related papers

Related papers: In-Context Planning with Latent Temporal Abstracti…

200 papers

We introduce the transport-and-pack(TAP) problem, a frequently encountered instance of real-world packing, and develop a neural optimization solution based on reinforcement learning. Given an initial spatial configuration of boxes, we seek…

Graphics · Computer Science 2020-09-04 Ruizhen Hu , Juzhan Xu , Bin Chen , Minglun Gong , Hao Zhang , Hui Huang

The recent offline reinforcement learning (RL) studies have achieved much progress to make RL usable in real-world systems by learning policies from pre-collected datasets without environment interaction. Unfortunately, existing offline RL…

Artificial Intelligence · Computer Science 2022-04-22 Xianyuan Zhan , Xiangyu Zhu , Haoran Xu

Current robots are capable of computing plans to accomplish complex tasks. However, real-world environments are inherently open and dynamic, and unforeseen situations frequently arise during plan execution, such as jamming doors and fallen…

Large-scale autoregressive models pretrained on next-token prediction and finetuned with reinforcement learning (RL) have achieved unprecedented success on many problem domains. During RL, these models explore by generating new outputs, one…

The combination of exponentially large action spaces, stochastic dynamics, and long-horizon decision-making under limited resources makes Sequential Stochastic Combinatorial Optimization (SSCO) particularly challenging for reinforcement…

Machine Learning · Computer Science 2026-05-19 Vivienne Huiling Wang , Tinghuai Wang , Joni Pajarinen

Multimodal in-context learning (ICL) has emerged as a key mechanism for harnessing the capabilities of large vision-language models (LVLMs). However, its effectiveness remains highly sensitive to the quality of input ICL sequences,…

Computation and Language · Computer Science 2025-10-22 Yanshu Li , Jianjiang Yang , Tian Yun , Pinyuan Feng , Jinfa Huang , Ruixiang Tang

Learning and planning with latent space dynamics has been shown to be useful for sample efficiency in model-based reinforcement learning (MBRL) for discrete and continuous control tasks. In particular, recent work, for discrete action…

Machine Learning · Computer Science 2020-10-21 Anurag Koul , Varun V. Kumar , Alan Fern , Somdeb Majumdar

Meta-planning, or learning to guide planning from experience, is a promising approach to improving the computational cost of planning. A general meta-planning strategy is to learn to impose constraints on the states considered and actions…

Machine Learning · Computer Science 2020-11-10 Rohan Chitnis , Tom Silver , Beomjoon Kim , Leslie Pack Kaelbling , Tomas Lozano-Perez

In the domain of combat simulations, the training and deployment of deep reinforcement learning (RL) agents still face substantial challenges due to the dynamic and intricate nature of such environments. Unfortunately, as the complexity of…

Machine Learning · Computer Science 2024-08-27 Scotty Black , Christian Darken

Decision-making in complex, continuous multi-task environments is often hindered by the difficulty of obtaining accurate models for planning and the inefficiency of learning purely from trial and error. While precise environment dynamics…

Machine Learning · Computer Science 2025-03-20 Jeff Jewett , Sandhya Saisubramanian

Temporal abstraction and efficient planning pose significant challenges in offline reinforcement learning, mainly when dealing with domains that involve temporally extended tasks and delayed sparse rewards. Existing methods typically plan…

Machine Learning · Computer Science 2023-10-03 Wenhao Li

In-context learning (ICL) is a key building block of modern large language models, yet its theoretical mechanisms remain poorly understood. It is particularly mysterious how ICL operates in real-world applications where tasks have a common…

Disordered Systems and Neural Networks · Physics 2026-04-24 Kaito Takanami , Takashi Takahashi , Yoshiyuki Kabashima

Path planning in dynamic environments is a fundamental challenge in intelligent transportation and robotics, where obstacles and conditions change over time, introducing uncertainty and requiring continuous adaptation. While existing…

Robotics · Computer Science 2025-11-20 Jonas De Maeyer , Hossein Yarahmadi , Moharram Challenger

Supervised learning approaches to offline reinforcement learning, particularly those utilizing the Decision Transformer, have shown effectiveness in continuous environments and for sparse rewards. However, they often struggle with…

Machine Learning · Computer Science 2024-09-17 Joseph Clinton , Robert Lieck

Informative path planning (IPP) is a crucial task in robotics, where agents must design paths to gather valuable information about a target environment while adhering to resource constraints. Reinforcement learning (RL) has been shown to be…

Robotics · Computer Science 2024-09-26 Srikar Babu Gadipudi , Srujan Deolasee , Siva Kailas , Wenhao Luo , Katia Sycara , Woojun Kim

Urban flow prediction is a classic spatial-temporal forecasting task that estimates the amount of future traffic flow for a given location. Though models represented by Spatial-Temporal Graph Neural Networks (STGNNs) have established…

Machine Learning · Computer Science 2024-12-10 Haiyang Jiang , Tong Chen , Wentao Zhang , Nguyen Quoc Viet Hung , Yuan Yuan , Yong Li , Lizhen Cui

Diffusion models achieve strong generative performance but remain slow at inference due to the need for repeated full-model denoising passes. We present Token-Adaptive Predictor (TAP), a training-free, probe-driven framework that adaptively…

Computer Vision and Pattern Recognition · Computer Science 2026-03-05 Haowei Zhu , Tingxuan Huang , Xing Wang , Tianyu Zhao , Jiexi Wang , Weifeng Chen , Xurui Peng , Fangmin Chen , Junhai Yong , Bin Wang

Current interactive LLM agents rely on goal-conditioned stepwise planning, where environmental understanding is acquired reactively during execution rather than established beforehand. This temporal inversion leads to Delayed Environmental…

Artificial Intelligence · Computer Science 2026-05-14 Yuxin Liu , Ziang Ye , Yueqing Sun , Mingye Zhu , Jinwei Xiao , Zhuowen Han , Qi GU , Xunliang Cai , Lei Zhang

Recent studies have shown that Transformers can perform in-context reinforcement learning (RL) by imitating existing RL algorithms, enabling sample-efficient adaptation to unseen tasks without parameter updates. However, these models also…

Machine Learning · Computer Science 2025-02-27 Jaehyeon Son , Soochan Lee , Gunhee Kim

Task and motion planning (TAMP) frameworks address long and complex planning problems by integrating high-level task planners with low-level motion planners. However, existing TAMP methods rely heavily on the manual design of planning…

Robotics · Computer Science 2025-09-09 Jinbang Huang , Allen Tao , Rozilyn Marco , Miroslav Bogdanovic , Jonathan Kelly , Florian Shkurti