40 citations · 80 across the 36 of their papers we have counts for
16 papers · 1 filter
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…
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…
Autonomous Aerial Manipulation via Contextual Contrastive Meta Reinforcement Learning
Lixuan Jin, Bingxuan Lan, Xinyi Bao +9
Unmanned aerial vehicles (UAVs) are increasingly being deployed in logistics, service robotics, and other real-world applications, creating a growing demand for autonomous payload…
Model-Based Proactive Cost Generation for Learning Safe Policies Offline with Limited Violation Data
Ruiqi Xue, Lei Yuan, Kainuo Cheng +2
Learning constraint-satisfying policies from offline data without risky online interaction is crucial for safety-critical decision making. Conventional methods typically learn cost…
Sequential Multi-Agent Dynamic Algorithm Configuration
Chen Lu, Ke Xue, Lei Yuan +4
Dynamic algorithm configuration (DAC) is a recent trend in automated machine learning, which can dynamically adjust the algorithm's configuration during the execution process and r…
SkillTree: Explainable Skill-Based Deep Reinforcement Learning for Long-Horizon Control Tasks
Yongyan Wen, Siyuan Li, Rongchang Zuo +3
Deep reinforcement learning (DRL) has achieved remarkable success in various research domains. However, its reliance on neural networks results in a lack of transparency, which lim…
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…
Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation
Yi-Chen Li, Fuxiang Zhang, Wenjie Qiu +5
Large Language Models (LLMs), trained on a large amount of corpus, have demonstrated remarkable abilities. However, it may not be sufficient to directly apply open-source LLMs like…
Disentangling Policy from Offline Task Representation Learning via Adversarial Data Augmentation
Chengxing Jia, Fuxiang Zhang, Yi-Chen Li +5
Offline meta-reinforcement learning (OMRL) proficiently allows an agent to tackle novel tasks while solely relying on a static dataset. For precise and efficient task identificatio…
Debiased Offline Representation Learning for Fast Online Adaptation in Non-stationary Dynamics
Xinyu Zhang, Wenjie Qiu, Yi-Chen Li +4
Developing policies that can adjust to non-stationary environments is essential for real-world reinforcement learning applications. However, learning such adaptable policies in off…
Efficient Human-AI Coordination via Preparatory Language-based Convention
Cong Guan, Lichao Zhang, Chunpeng Fan +6
Developing intelligent agents capable of seamless coordination with humans is a critical step towards achieving artificial general intelligence. Existing methods for human-AI coord…
Communication-Robust Multi-Agent Learning by Adaptable Auxiliary Multi-Agent Adversary Generation
Lei Yuan, Feng Chen, Zhongzhang Zhang +1
Communication can promote coordination in cooperative Multi-Agent Reinforcement Learning (MARL). Nowadays, existing works mainly focus on improving the communication efficiency of…
Efficient Communication via Self-supervised Information Aggregation for Online and Offline Multi-agent Reinforcement Learning
Cong Guan, Feng Chen, Lei Yuan +2
Utilizing messages from teammates can improve coordination in cooperative Multi-agent Reinforcement Learning (MARL). Previous works typically combine raw messages of teammates with…
Self-Motivated Multi-Agent Exploration
Shaowei Zhang, Jiahan Cao, Lei Yuan +2
In cooperative multi-agent reinforcement learning (CMARL), it is critical for agents to achieve a balance between self-exploration and team collaboration. However, agents can hardl…
Multi-agent Dynamic Algorithm Configuration
Ke Xue, Jiacheng Xu, Lei Yuan +4
Automated algorithm configuration relieves users from tedious, trial-and-error tuning tasks. A popular algorithm configuration tuning paradigm is dynamic algorithm configuration (D…
LINDA: Multi-Agent Local Information Decomposition for Awareness of Teammates
Jiahan Cao, Lei Yuan, Jianhao Wang +4
In cooperative multi-agent reinforcement learning (MARL), where agents only have access to partial observations, efficiently leveraging local information is critical. During long-t…