中文
相关论文

相关论文: Vintix II: Decision Pre-Trained Transformer is a S…

200 篇论文

Post-training endows pretrained LLMs with a variety of desirable skills, including instruction-following, reasoning, and others. However, these post-trained LLMs only encode knowledge up to a cut-off date, necessitating continual…

计算与语言 · 计算机科学 2026-02-19 Shankar Padmanabhan , Mustafa Omer Gul , Tanya Goyal

In natural language processing (NLP) tasks, slow inference speed and huge footprints in GPU usage remain the bottleneck of applying pre-trained deep models in production. As a popular method for model compression, knowledge distillation…

计算与语言 · 计算机科学 2020-12-15 Fei Yuan , Linjun Shou , Jian Pei , Wutao Lin , Ming Gong , Yan Fu , Daxin Jiang

Partial observability is a notorious challenge in reinforcement learning (RL), due to the need to learn complex, history-dependent policies. Recent empirical successes have used privileged expert distillation--which leverages availability…

机器学习 · 计算机科学 2025-10-06 Yuda Song , Dhruv Rohatgi , Aarti Singh , J. Andrew Bagnell

Robot learning requires adaptation methods that improve reliably from limited, mixed-quality interaction data. This is especially challenging in long-horizon, contact-rich tasks, where end-to-end policy finetuning remains inefficient and…

Recent advances in Reinforcement Learning (RL) largely benefit from the inclusion of Deep Neural Networks, boosting the number of novel approaches proposed in the field of Deep Reinforcement Learning (DRL). These techniques demonstrate the…

机器学习 · 计算机科学 2025-07-30 Giovanni Dispoto , Paolo Bonetti , Marcello Restelli

Action-constrained reinforcement learning (ACRL) is a popular approach for solving safety-critical and resource-allocation related decision making problems. A major challenge in ACRL is to ensure agent taking a valid action satisfying…

机器学习 · 计算机科学 2024-02-09 Janaka Chathuranga Brahmanage , Jiajing Ling , Akshat Kumar

Reinforcement Learning (RL) and Deep Reinforcement Learning (DRL) have advanced rapidly in recent years and have been successfully applied to e-learning environments like intelligent tutoring systems (ITSs). Despite great success, the…

机器学习 · 计算机科学 2026-02-25 Md Mirajul Islam , Xi Yang , Adittya Soukarjya Saha , Rajesh Debnath , Min Chi

Maritime autonomous transportation has played a crucial role in the globalization of the world economy. Deep Reinforcement Learning (DRL) has been applied to automatic path planning to simulate vessel collision avoidance situations in open…

人工智能 · 计算机科学 2021-06-29 Nader Zare , Bruno Brandoli , Mahtab Sarvmaili , Amilcar Soares , Stan Matwin

Designing better deep networks and better reinforcement learning (RL) algorithms are both important for deep RL. This work studies the former. Specifically, the Perception and Decision-making Interleaving Transformer (PDiT) network is…

机器学习 · 计算机科学 2023-12-27 Hangyu Mao , Rui Zhao , Ziyue Li , Zhiwei Xu , Hao Chen , Yiqun Chen , Bin Zhang , Zhen Xiao , Junge Zhang , Jiangjin Yin

The recent success of denoising diffusion models has significantly advanced text-to-image generation. While these large-scale pretrained models show excellent performance in general image synthesis, downstream objectives often require…

计算机视觉与模式识别 · 计算机科学 2024-11-27 Maorong Wang , Jiafeng Mao , Xueting Wang , Toshihiko Yamasaki

With the development of deep representation learning, the domain of reinforcement learning (RL) has become a powerful learning framework now capable of learning complex policies in high dimensional environments. This review summarises deep…

Recent Vision-Language-Action (VLA) models have shown impressive flexibility and generalization, yet their deployment in robotic manipulation remains limited by heavy computational overhead and inference latency. In this work, we present…

计算机视觉与模式识别 · 计算机科学 2026-04-14 Wencheng Ye , Tianshi Wang , Lei Zhu , Fengling Li , Guoli Yang , Hengtao Shen

In-Context Reinforcement Learning (ICRL) is a frontier paradigm to solve Reinforcement Learning (RL) problems in the foundation model era. While ICRL capabilities have been demonstrated in transformers through task-specific training, the…

机器学习 · 计算机科学 2025-06-10 Fanzeng Xia , Hao Liu , Yisong Yue , Tongxin Li

Language model (LM) post-training (or alignment) involves maximizing a reward function that is derived from preference annotations. Direct Preference Optimization (DPO) is a popular offline alignment method that trains a policy directly on…

The use of Reinforcement Learning (RL) agents in practical applications requires the consideration of suboptimal outcomes, depending on the familiarity of the agent with its environment. This is especially important in safety-critical…

机器学习 · 计算机科学 2021-12-07 Frederik Schubert , Theresa Eimer , Bodo Rosenhahn , Marius Lindauer

With the implementation of reinforcement learning (RL) algorithms, current state-of-art autonomous vehicle technology have the potential to get closer to full automation. However, most of the applications have been limited to game domains…

机器人学 · 计算机科学 2020-01-14 Wenhui Huang , Francesco Braghin , Zhuo Wang

Prompt learning as a parameter-efficient method that has been widely adopted to adapt Vision-Language Models (VLMs) to downstream tasks. While hard-prompt design requires domain expertise and iterative optimization, soft-prompt methods rely…

计算机视觉与模式识别 · 计算机科学 2025-05-26 Zherui Zhang , Jiaxin Wu , Changwei Wang , Rongtao Xu , Longzhao Huang , Wenhao Xu , Wenbo Xu , Li Guo , Shibiao Xu

Pre-trained language models (e.g., BERT (Devlin et al., 2018) and its variants) have achieved remarkable success in varieties of NLP tasks. However, these models usually consist of hundreds of millions of parameters which brings challenges…

计算与语言 · 计算机科学 2020-04-07 Wenhui Wang , Furu Wei , Li Dong , Hangbo Bao , Nan Yang , Ming Zhou

Safe Reinforcement Learning (RL) aims to find a policy that achieves high rewards while satisfying cost constraints. When learning from scratch, safe RL agents tend to be overly conservative, which impedes exploration and restrains the…

机器人学 · 计算机科学 2023-10-16 Jinning Li , Xinyi Liu , Banghua Zhu , Jiantao Jiao , Masayoshi Tomizuka , Chen Tang , Wei Zhan

We consider a context-dependent Reinforcement Learning (RL) setting, which is characterized by: a) an unknown finite number of not directly observable contexts; b) abrupt (discontinuous) context changes occurring during an episode; and c)…

机器学习 · 计算机科学 2022-02-15 Hang Ren , Aivar Sootla , Taher Jafferjee , Junxiao Shen , Jun Wang , Haitham Bou-Ammar