1 citations · 2 across the 15 of their papers we have counts for
15 papers
Prioritized Rollouts for Efficient World Model-based Vision-Language-Action Policy Optimization
Yifei Sheng, Haoxiang Ren, Zhilong Zhang +8
Vision-Language-Action (VLA) models have emerged as a powerful paradigm for embodied intelligence, but fine-tuning them with reinforcement learning (RL) remains constrained by the…
Weak-to-Strong Generalization via Direct On-Policy Distillation
Shiyuan Feng, Huan-ang Gao, Haohan Chi +7
Reinforcement learning with verifiable rewards (RLVR) is a powerful recipe for improving language-model reasoning, but it is expensive to repeat on every new strong model because t…
Provably Efficient Policy-Reward Co-Pretraining for Adversarial Imitation Learning
Tian Xu, Zexuan Chen, Zhilong Zhang +4
Adversarial imitation learning (AIL) achieves high-quality imitation compared to behavioral cloning (BC), but demands substantial online environment interaction. Recent empirical w…
Continual Quadruped Robots Coordination via Semantic Skill Discovery
Daoqing Wang, Yuchen Xiao, Weixuan Huang +5
Multi-quadruped coordination has attracted increasing attention due to its enhanced payload capacity, broader contact coverage, and improved adaptability to challenging tasks. Exis…
Adversarial Imitation Learning with General Function Approximation: Theoretical Analysis and Practical Algorithms
Tian Xu, Zhilong Zhang, Zexuan Chen +3
Adversarial imitation learning (AIL), a prominent approach in imitation learning, has achieved significant practical success powered by neural network approximation. However, exist…
Anticipation-VLA: Solving Long-Horizon Embodied Tasks via Anticipation-based Subgoal Generation
Zhilong Zhang, Wenyu Luo, Haonan Wang +9
Vision-Language-Action (VLA) models have emerged as a powerful paradigm for embodied intelligence, enabling robots to perform tasks based on natural language instructions and curre…
Speedup Patch: Learning a Plug-and-Play Policy to Accelerate Embodied Manipulation
Zhichao Wu, Junyin Ye, Zhilong Zhang +6
While current embodied policies exhibit remarkable manipulation skills, their execution remains unsatisfactorily slow as they inherit the tardy pacing of human demonstrations. Exis…
Towards Practical World Model-based Reinforcement Learning for Vision-Language-Action Models
Zhilong Zhang, Haoxiang Ren, Yihao Sun +6
Vision-Language-Action (VLA) models show strong generalization for robotic control, but finetuning them with reinforcement learning (RL) is constrained by the high cost and safety…
Planning with Unified Multimodal Models
Yihao Sun, Zhilong Zhang, Yang Yu +1
With the powerful reasoning capabilities of large language models (LLMs) and vision-language models (VLMs), many recent works have explored using them for decision-making. However,…
Stable Continual Reinforcement Learning via Diffusion-based Trajectory Replay
Feng Chen, Fuguang Han, Cong Guan +4
Given the inherent non-stationarity prevalent in real-world applications, continual Reinforcement Learning (RL) aims to equip the agent with the capability to address a series of s…
WHALE: Towards Generalizable and Scalable World Models for Embodied Decision-making
Zhilong Zhang, Ruifeng Chen, Junyin Ye +8
World models play a crucial role in decision-making within embodied environments, enabling cost-free explorations that would otherwise be expensive in the real world. To facilitate…
Provably and Practically Efficient Adversarial Imitation Learning with General Function Approximation
Tian Xu, Zhilong Zhang, Ruishuo Chen +2
As a prominent category of imitation learning methods, adversarial imitation learning (AIL) has garnered significant practical success powered by neural network approximation. Howe…
Energy-Guided Diffusion Sampling for Offline-to-Online Reinforcement Learning
Xu-Hui Liu, Tian-Shuo Liu, Shengyi Jiang +4
Combining offline and online reinforcement learning (RL) techniques is indeed crucial for achieving efficient and safe learning where data acquisition is expensive. Existing method…
BWArea Model: Learning World Model, Inverse Dynamics, and Policy for Controllable Language Generation
Chengxing Jia, Pengyuan Wang, Ziniu Li +4
Large language models (LLMs) have catalyzed a paradigm shift in natural language processing, yet their limited controllability poses a significant challenge for downstream applicat…
Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning
Haoxin Lin, Yu-Yan Xu, Yihao Sun +6
Model-based methods in reinforcement learning offer a promising approach to enhance data efficiency by facilitating policy exploration within a dynamics model. However, accurately…