2 citations · 3 across the 18 of their papers we have counts for
23 papers
TSRL: Trigger-based Supervised Reinforcement Learning for Continual Agent Training
Yuqian Fu, Kaiwen Jiang, Zijun Song +3
Large language model (LLM) agents excel at complex, multi-step tasks but suffer from catastrophic forgetting during continual learning--acquiring new skills often degrades previous…
Harnessing VLM in Embodied RL: From Reward Regressor to Success Detector via Exploration-Augmented Key-Observation Gating
Xin Liu, Yutong Jiang, Jian Su +4
VLMs provide promising solutions to embodied reward design. Most current methods that train VLMs as reward regressors not only require extensive annotations but are also primarily…
LocoWM: High-Precision Locomotion through World-Model-Guided Residual Adaptation
Zijie Zhao, Shengqian Chen, Xiaoxu Wang +3
High-precision locomotion combines motion-command tracking with precise regulation of task-relevant physical states, enabling robots to interact reliably with their surroundings du…
Are Full Rollouts Necessary for On-Policy Distillation?
Yaocheng Zhang, Jiajun Chai, Yuqian Fu +7
On-policy distillation (OPD) provides dense teacher feedback along student-generated rollouts rather than fixed teacher traces and has emerged as a promising post-training paradigm…
-Play: Multi-Agent Self-Play via Privileged Self-Distillation without External Data
Yaocheng Zhang, Yuanheng Zhu, Wenyue Chong +7
Deep search agents have emerged as a promising paradigm for addressing complex information-seeking tasks, but their training remains challenging due to sparse rewards, weak credit…
Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes
Yuqian Fu, Haohuan Huang, Kaiwen Jiang +4
On-policy distillation (OPD) is increasingly used in LLM post-training because it can leverage a teacher model to provide dense supervision on student rollouts. The standard implem…
Equilibrium Policy Generalization: A Reinforcement Learning Framework for Cross-Graph Zero-Shot Generalization in Pursuit-Evasion Games
Runyu Lu, Peng Zhang, Ruochuan Shi +5
Equilibrium learning in adversarial games is an important topic widely examined in the fields of game theory and reinforcement learning (RL). Pursuit-evasion game (PEG), as an impo…
CriticSearch: Fine-Grained Credit Assignment for Search Agents via a Retrospective Critic
Yaocheng Zhang, Haohuan Huang, Zijun Song +4
Tool-Integrated Reasoning (TIR) with search engines enables large language models to iteratively retrieve up-to-date external knowledge, enhancing adaptability and generalization i…
ARAC: Adaptive Regularized Multi-Agent Soft Actor-Critic in Graph-Structured Adversarial Games
Ruochuan Shi, Runyu Lu, Yuanheng Zhu +1
In graph-structured multi-agent reinforcement learning (MARL) adversarial tasks such as pursuit and confrontation, agents must coordinate under highly dynamic interactions, where s…
R2PS: Worst-Case Robust Real-Time Pursuit Strategies under Partial Observability
Runyu Lu, Ruochuan Shi, Yuanheng Zhu +1
Computing worst-case robust strategies in pursuit-evasion games (PEGs) is time-consuming, especially when real-world factors like partial observability are considered. While import…
Empowering Multi-Robot Cooperation via Sequential World Models
Zijie Zhao, Honglei Guo, Shengqian Chen +4
Model-based reinforcement learning (MBRL) has achieved remarkable success in robotics due to its high sample efficiency and planning capability. However, extending MBRL to physical…
SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning
Yuqian Fu, Tinghong Chen, Jiajun Chai +7
Large language models (LLMs) have achieved remarkable progress in reasoning tasks, yet the optimal integration of Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) remai…
TeViR: Text-to-Video Reward with Diffusion Models for Efficient Reinforcement Learning
Yuhui Chen, Haoran Li, Zhennan Jiang +2
Developing scalable and generalizable reward engineering for reinforcement learning (RL) is crucial for creating general-purpose agents, especially in the challenging domain of rob…
DipLLM: Fine-Tuning LLM for Strategic Decision-making in Diplomacy
Kaixuan Xu, Jiajun Chai, Sicheng Li +3
Diplomacy is a complex multiplayer game that requires both cooperation and competition, posing significant challenges for AI systems. Traditional methods rely on equilibrium search…
RLAE: Reinforcement Learning-Assisted Ensemble for LLMs
Yuqian Fu, Yuanheng Zhu, Jiajun Chai +4
Ensembling large language models (LLMs) can effectively combine diverse strengths of different models, offering a promising approach to enhance performance across various tasks. Ho…
ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy
Yuhui Chen, Shuai Tian, Shugao Liu +3
Vision-Language-Action (VLA) models have shown substantial potential in real-world robotic manipulation. However, fine-tuning these models through supervised learning struggles to…
CPIG: Leveraging Consistency Policy with Intention Guidance for Multi-agent Exploration
Yuqian Fu, Yuanheng Zhu, Haoran Li +3
Efficient exploration is crucial in cooperative multi-agent reinforcement learning (MARL), especially in sparse-reward settings. However, due to the reliance on the unimodal policy…
Generalizing Consistency Policy to Visual RL with Prioritized Proximal Experience Regularization
Haoran Li, Zhennan Jiang, Yuhui Chen +1
With high-dimensional state spaces, visual reinforcement learning (RL) faces significant challenges in exploitation and exploration, resulting in low sample efficiency and training…
Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement
Zhi Wang, Li Zhang, Wenhao Wu +3
A longstanding goal of artificial general intelligence is highly capable generalists that can learn from diverse experiences and generalize to unseen tasks. The language and vision…
SELU: Self-Learning Embodied MLLMs in Unknown Environments
Boyu Li, Haobin Jiang, Ziluo Ding +4
Recently, multimodal large language models (MLLMs) have demonstrated strong visual understanding and decision-making capabilities, enabling the exploration of autonomously improvin…
Discretizing Continuous Action Space with Unimodal Probability Distributions for On-Policy Reinforcement Learning
Yuanyang Zhu, Zhi Wang, Yuanheng Zhu +2
For on-policy reinforcement learning, discretizing action space for continuous control can easily express multiple modes and is straightforward to optimize. However, without consid…
FM3Q: Factorized Multi-Agent MiniMax Q-Learning for Two-Team Zero-Sum Markov Game
Guangzheng Hu, Yuanheng Zhu, Haoran Li +1
Many real-world applications involve some agents that fall into two teams, with payoffs that are equal within the same team but of opposite sign across the opponent team. The so-ca…
Boosting Continuous Control with Consistency Policy
Yuhui Chen, Haoran Li, Dongbin Zhao
Due to its training stability and strong expression, the diffusion model has attracted considerable attention in offline reinforcement learning. However, several challenges have al…