中文
相关论文

相关论文: Compositional Transduction with Latent Analogies f…

200 篇论文

In this study, we address the challenge of learning generalizable policies for compositional tasks defined by logical specifications. These tasks consist of multiple temporally extended sub-tasks. Due to the sub-task inter-dependencies and…

人工智能 · 计算机科学 2024-11-05 Duo Xu , Faramarz Fekri

Offline goal-conditioned reinforcement learning (GCRL) provides a practical framework for obtaining goal-reaching policies from fixed datasets. However, learning a reliable goal-conditioned value function in long-horizon tasks remains…

机器学习 · 计算机科学 2026-05-26 Hyungkyu Kang , Byeongchan Kim , Min-hwan Oh

The ability to generalize to previously unseen tasks with little to no supervision is a key challenge in modern machine learning research. It is also a cornerstone of a future "General AI". Any artificially intelligent agent deployed in a…

机器学习 · 计算机科学 2022-07-26 Xihan Bian , Oscar Mendez , Simon Hadfield

Approaches for goal-conditioned reinforcement learning (GCRL) often use learned state representations to extract goal-reaching policies. Two frameworks for representation structure have yielded particularly effective GCRL algorithms: (1)…

机器学习 · 计算机科学 2025-12-03 Vivek Myers , Bill Chunyuan Zheng , Benjamin Eysenbach , Sergey Levine

Offline goal-conditioned reinforcement learning (GCRL) is a major problem in reinforcement learning (RL) because it provides a simple, unsupervised, and domain-agnostic way to acquire diverse behaviors and representations from unlabeled…

机器学习 · 计算机科学 2025-02-14 Seohong Park , Kevin Frans , Benjamin Eysenbach , Sergey Levine

Offline goal-conditioned RL (GCRL) offers a way to train general-purpose agents from fully offline datasets. In addition to being conservative within the dataset, the generalization ability to achieve unseen goals is another fundamental…

机器学习 · 计算机科学 2023-06-05 Rui Yang , Yong Lin , Xiaoteng Ma , Hao Hu , Chongjie Zhang , Tong Zhang

Offline Goal-Conditioned RL (GCRL) offers a feasible paradigm for learning general-purpose policies from diverse and multi-task offline datasets. Despite notable recent progress, the predominant offline GCRL methods, mainly model-free, face…

机器学习 · 计算机科学 2024-05-17 Mianchu Wang , Rui Yang , Xi Chen , Hao Sun , Meng Fang , Giovanni Montana

Compositional generalization refers to correctly interpret novel combinations of known primitives, which remains a major challenge. Existing approaches often rely on supervised fine-tuning, which encourages models to imitate target outputs.…

机器学习 · 计算机科学 2026-05-07 Xiyan Fu , Wei Liu

Goal-conditioned reinforcement learning (GCRL) refers to learning general-purpose skills that aim to reach diverse goals. In particular, offline GCRL only requires purely pre-collected datasets to perform training tasks without additional…

机器学习 · 计算机科学 2023-10-13 Hanlin Zhu , Amy Zhang

Despite the broad application of deep reinforcement learning (RL), transferring and adapting the policy to unseen but similar environments is still a significant challenge. Recently, the language-conditioned policy is proposed to facilitate…

机器学习 · 计算机科学 2023-03-10 Shaohui Peng , Xing Hu , Rui Zhang , Jiaming Guo , Qi Yi , Ruizhi Chen , Zidong Du , Ling Li , Qi Guo , Yunji Chen

Offline Meta Reinforcement Learning (OMRL) aims to learn transferable knowledge from offline datasets to enhance the learning process for new target tasks. Context-based Reinforcement Learning (RL) adopts a context encoder to expediently…

机器学习 · 计算机科学 2023-05-24 Chenyang Zhao , Zihao Zhou , Bin Liu

Neural network models often generalize poorly to mismatched domains or distributions. In NLP, this issue arises in particular when models are expected to generalize compositionally, that is, to novel combinations of familiar words and…

计算与语言 · 计算机科学 2021-11-10 Wang Zhu , Peter Shaw , Tal Linzen , Fei Sha

Accurate estimation of the Q-function is a central challenge in offline reinforcement learning. However, existing approaches often rely on a shared global Q-function, which is inadequate for capturing the compositional structure of tasks…

机器学习 · 计算机科学 2026-03-19 Qiushui Xu , Yuhao Huang , Yushu Jiang , Lei Song , Jinyu Wang , Wenliang Zheng , Jiang Bian

Offline goal-conditioned reinforcement learning (GCRL) is a practical reinforcement learning paradigm that aims to learn goal-conditioned policies from reward-free offline data. Despite recent advances in hierarchical architectures such as…

机器学习 · 计算机科学 2026-04-13 Zhiqiang Dong , Teng Pang , Rongjian Xu , Guoqiang Wu

Offline goal-conditioned reinforcement learning (GCRL) is a promising approach for pretraining generalist policies on large datasets of reward-free trajectories, akin to the self-supervised objectives used to train foundation models for…

机器学习 · 计算机科学 2026-01-05 John L. Zhou , Jonathan C. Kao

Despite recent progress in offline learning, these methods are still trained and tested on the same environment. In this paper, we compare the generalization abilities of widely used online and offline learning methods such as online…

机器学习 · 计算机科学 2024-03-18 Ishita Mediratta , Qingfei You , Minqi Jiang , Roberta Raileanu

Offline goal-conditioned reinforcement learning (GCRL) aims at solving goal-reaching tasks with sparse rewards from an offline dataset. While prior work has demonstrated various approaches for agents to learn near-optimal policies, these…

机器人学 · 计算机科学 2024-03-05 Chenyang Cao , Zichen Yan , Renhao Lu , Junbo Tan , Xueqian Wang

Offline reinforcement learning (RL) optimizes the policy on a previously collected dataset without any interactions with the environment, yet usually suffers from the distributional shift problem. To mitigate this issue, a typical solution…

机器学习 · 计算机科学 2023-09-06 Qisen Yang , Shenzhi Wang , Qihang Zhang , Gao Huang , Shiji Song

Compositional generalization is a basic mechanism in human language learning, which current neural networks struggle with. A recently proposed Disentangled sequence-to-sequence model (Dangle) shows promising generalization capability by…

计算与语言 · 计算机科学 2022-12-13 Hao Zheng , Mirella Lapata

Context-based offline meta-reinforcement learning (OMRL) methods have achieved appealing success by leveraging pre-collected offline datasets to develop task representations that guide policy learning. However, current context-based OMRL…

机器学习 · 计算机科学 2025-02-04 Zhengzhe Zhang , Wenjia Meng , Haoliang Sun , Gang Pan
‹ 上一页 1 2 3 10 下一页 ›