中文
相关论文

相关论文: Hierarchical Prompt Decision Transformer: Improvin…

200 篇论文

Humans can leverage prior experience and learn novel tasks from a handful of demonstrations. In contrast to offline meta-reinforcement learning, which aims to achieve quick adaptation through better algorithm design, we investigate the…

机器学习 · 计算机科学 2022-06-28 Mengdi Xu , Yikang Shen , Shun Zhang , Yuchen Lu , Ding Zhao , Joshua B. Tenenbaum , Chuang Gan

Decision Transformer (DT) is an innovative algorithm leveraging recent advances of the transformer architecture in reinforcement learning (RL). However, a notable limitation of DT is its reliance on recalling trajectories from datasets,…

机器学习 · 计算机科学 2023-11-02 Yi Ma , Chenjun Xiao , Hebin Liang , Jianye Hao

Prompting method is regarded as one of the crucial progress for few-shot nature language processing. Recent research on prompting moves from discrete tokens based ``hard prompts'' to continuous ``soft prompts'', which employ learnable…

计算与语言 · 计算机科学 2023-02-06 Yutai Hou , Hongyuan Dong , Xinghao Wang , Bohan Li , Wanxiang Che

We present a hierarchical neuro-symbolic control framework that tightly couples a classical symbolic planner with a transformer-based policy to address long-horizon decision-making under uncertainty. At the high level, the planner assembles…

人工智能 · 计算机科学 2025-05-30 Ali Baheri , Cecilia O. Alm

Sequence models in reinforcement learning require task knowledge to estimate the task policy. This paper presents a hierarchical algorithm for learning a sequence model from demonstrations. The high-level mechanism guides the low-level…

机器学习 · 计算机科学 2022-09-22 André Correia , Luís A. Alexandre

Hierarchical reinforcement learning is a promising approach to tackle long-horizon decision-making problems with sparse rewards. Unfortunately, most methods still decouple the lower-level skill acquisition process and the training of a…

机器学习 · 计算机科学 2020-05-15 Alexander C. Li , Carlos Florensa , Ignasi Clavera , Pieter Abbeel

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…

机器学习 · 计算机科学 2025-03-20 Jeff Jewett , Sandhya Saisubramanian

Multi-objective Markov decision processes are sequential decision-making problems that involve multiple conflicting reward functions that cannot be optimized simultaneously without a compromise. This type of problems cannot be solved by a…

机器学习 · 计算机科学 2023-08-22 Sherif Abdelfattah , Kathryn Merrick , Jiankun Hu

This paper describes a purely data-driven solution to a class of sequential decision-making problems with a large number of concurrent online decisions, with applications to computing systems and operations research. We assume that while…

人工智能 · 计算机科学 2019-10-02 Hardik Meisheri , Vinita Baniwal , Nazneen N Sultana , Balaraman Ravindran , Harshad Khadilkar

The emergence of attention-based transformer models has led to their extensive use in various tasks, due to their superior generalization and transfer properties. Recent research has demonstrated that such models, when prompted…

计算机视觉与模式识别 · 计算机科学 2024-04-19 Mir Rayat Imtiaz Hossain , Mennatullah Siam , Leonid Sigal , James J. Little

Motivation: Disease diagnosis oriented dialogue system models the interactive consultation procedure as Markov Decision Process and reinforcement learning algorithms are used to solve the problem. Existing approaches usually employ a flat…

人工智能 · 计算机科学 2023-11-08 Cheng Zhong , Kangenbei Liao , Wei Chen , Qianlong Liu , Baolin Peng , Xuanjing Huang , Jiajie Peng , Zhongyu Wei

Transformers have demonstrated exceptional in-context learning (ICL) capabilities, enabling applications across natural language processing, computer vision, and sequential decision-making. In reinforcement learning, ICL reframes learning…

机器学习 · 计算机科学 2025-11-14 Oliver Dippel , Alexei Lisitsa , Bei Peng

In-context learning is a promising approach for offline reinforcement learning (RL) to handle online tasks, which can be achieved by providing task prompts. Recent works demonstrated that in-context RL could emerge with self-improvement in…

机器学习 · 计算机科学 2024-06-03 Sili Huang , Jifeng Hu , Hechang Chen , Lichao Sun , Bo Yang

To make good decisions in the real world people need efficient planning strategies because their computational resources are limited. Knowing which planning strategies would work best for people in different situations would be very useful…

人工智能 · 计算机科学 2021-02-02 Saksham Consul , Lovis Heindrich , Jugoslav Stojcheski , Falk Lieder

Complex, multi-task problems have proven to be difficult to solve efficiently in a sparse-reward reinforcement learning setting. In order to be sample efficient, multi-task learning requires reuse and sharing of low-level policies. To…

机器学习 · 计算机科学 2021-09-28 Valerie Chen , Abhinav Gupta , Kenneth Marino

Continual learning endeavors to equip the model with the capability to integrate current task knowledge while mitigating the forgetting of past task knowledge. Inspired by prompt tuning, prompt-based methods maintain a frozen backbone and…

计算机视觉与模式识别 · 计算机科学 2024-01-23 Yukun Zuo , Hantao Yao , Lu Yu , Liansheng Zhuang , Changsheng Xu

Transformer-based methods have exhibited significant generalization ability when prompted with target-domain demonstrations or example solutions during inference. Although demonstrations, as a way of task specification, can capture rich…

机器学习 · 计算机科学 2024-05-13 Meng Song , Xuezhi Wang , Tanay Biradar , Yao Qin , Manmohan Chandraker

Despite recent advances in learning-based behavioral planning for autonomous systems, decision-making in multi-task missions remains a challenging problem. For instance, a mission might require a robot to explore an unknown environment,…

机器人学 · 计算机科学 2024-12-03 Akash Karthikeyan , Yash Vardhan Pant

Reinforcement learning methods can achieve significant performance but require a large amount of training data collected on the same robotic platform. A policy trained with expensive data is rendered useless after making even a minor change…

机器人学 · 计算机科学 2021-03-08 Ali Ghadirzadeh , Xi Chen , Petra Poklukar , Chelsea Finn , Mårten Björkman , Danica Kragic

Catastrophic forgetting poses a substantial challenge for managing intelligent agents controlled by a large model, causing performance degradation when these agents face new tasks. In our work, we propose a novel solution - the Progressive…

机器学习 · 计算机科学 2025-09-04 Zhiyuan Wang , Xiaoyang Qu , Jing Xiao , Bokui Chen , Jianzong Wang
‹ 上一页 1 2 3 10 下一页 ›