11 citations · 11 across the 7 of their papers we have counts for
7 papers
ExToken: Structured Exploration for Efficient Vision-Language-Action Reinforcement Fine-tuning
Yilun Kong, Yunpeng Qing, Guozheng Ma +4
Reinforcement Learning (RL) has demonstrated significant potential for improving Vision-Language-Action (VLA) models on complex manipulation tasks. However, its practical scalabili…
Decision Flow Policy Optimization
Jifeng Hu, Sili Huang, Siyuan Guo +6
In recent years, generative models have shown remarkable capabilities across diverse fields, including images, videos, language, and decision-making. By applying powerful generativ…
Neuron-level Balance between Stability and Plasticity in Deep Reinforcement Learning
Jiahua Lan, Sen Zhang, Haixia Pan +3
In contrast to the human ability to continuously acquire knowledge, agents struggle with the stability-plasticity dilemma in deep reinforcement learning (DRL), which refers to the…
Solving Continual Offline RL through Selective Weights Activation on Aligned Spaces
Jifeng Hu, Sili Huang, Li Shen +7
Continual offline reinforcement learning (CORL) has shown impressive ability in diffusion-based lifelong learning systems by modeling the joint distributions of trajectories. Howev…
Continual Diffuser (CoD): Mastering Continual Offline Reinforcement Learning with Experience Rehearsal
Jifeng Hu, Li Shen, Sili Huang +5
Artificial neural networks, especially recent diffusion-based models, have shown remarkable superiority in gaming, control, and QA systems, where the training tasks' datasets are u…
QPO: Query-dependent Prompt Optimization via Multi-Loop Offline Reinforcement Learning
Yilun Kong, Hangyu Mao, Qi Zhao +7
Prompt engineering has demonstrated remarkable success in enhancing the performance of large language models (LLMs) across diverse tasks. However, most existing prompt optimization…
Revisiting Discrete Soft Actor-Critic
Haibin Zhou, Tong Wei, Zichuan Lin +6
We study the adaption of Soft Actor-Critic (SAC), which is considered as a state-of-the-art reinforcement learning (RL) algorithm, from continuous action space to discrete action s…