38 citations · 128 across the 30 of their papers we have counts for
30 papers
CORA: Analyzing and bridging thinking-answer gap in Multimodal RLVR via Consistency-Oriented Reasoning Alignment
Jiayue Cao, Zhicong Lu, Xuehan Sun +6
Reinforcement learning with verifiable rewards (RLVR) has successfully elicited the reasoning capabilities of large language models, motivating its extension to multimodal scenario…
Faithful-MR1: Faithful Multimodal Reasoning via Anchoring and Reinforcing Visual Attention
Changyuan Tian, Zhicong Lu, Huaxing Liu +7
Reinforcement learning with verifiable rewards (RLVR) has emerged as a promising paradigm for advancing complex reasoning in large language models, and recent work extends RLVR to…
Debiased Model-based Representations for Sample-efficient Continuous Control
Jiafei Lyu, Zichuan Lin, Scott Fujimoto +5
Model-based representations recently stand out as a promising framework that embeds latent dynamics information into the representations for downstream off-policy actor-critic lear…
HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation
He Zhao, Yijun Yang, Zichuan Lin +2
Embodied navigation agents built upon large reasoning models (LRMs) can handle complex, multimodal environmental input and perform grounded reasoning per step to improve sequential…
UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience
Zichuan Lin, Feiyu Liu, Yijun Yang +9
Autonomous mobile GUI agents have attracted increasing attention along with the advancement of Multimodal Large Language Models (MLLMs). However, existing methods still suffer from…
HISR: Hindsight Information Modulated Segmental Process Rewards For Multi-turn Agentic Reinforcement Learning
Zhicong Lu, Zichuan Lin, Wei Jia +7
While large language models excel in diverse domains, their performance on complex longhorizon agentic decision-making tasks remains limited. Most existing methods concentrate on d…
Cross-Domain Offline Policy Adaptation via Selective Transition Correction
Mengbei Yan, Jiafei Lyu, Shengjie Sun +5
It remains a critical challenge to adapt policies across domains with mismatched dynamics in reinforcement learning (RL). In this paper, we study cross-domain offline RL, where an…
ProAct: Agentic Lookahead in Interactive Environments
Yangbin Yu, Mingyu Yang, Junyou Li +9
Existing Large Language Model (LLM) agents struggle in interactive environments requiring long-horizon planning, primarily due to compounding errors when simulating future states.…
PIPCFR: Pseudo-outcome Imputation with Post-treatment Variables for Individual Treatment Effect Estimation
Zichuan Lin, Xiaokai Huang, Jiate Liu +4
The estimation of individual treatment effects (ITE) focuses on predicting the outcome changes that result from a change in treatment. A fundamental challenge in observational data…
SeeNav-Agent: Enhancing Vision-Language Navigation with Visual Prompt and Step-Level Policy Optimization
Zhengcheng Wang, Zichuan Lin, Yijun Yang +2
Existing Vision-Language Navigation (VLN) agents based on Large Vision-Language Models (LVLMs) often suffer from perception errors, reasoning errors, and planning errors, which sig…
AdaptVision: Efficient Vision-Language Models via Adaptive Visual Acquisition
Zichuan Lin, Yicheng Liu, Yang Yang +2
Vision-Language Models (VLMs) have achieved remarkable success in visual question answering tasks, but their reliance on large numbers of visual tokens introduces significant compu…
Multi-agent In-context Coordination via Decentralized Memory Retrieval
Tao Jiang, Zichuan Lin, Lihe Li +6
Large transformer models, trained on diverse datasets, have demonstrated impressive few-shot performance on previously unseen tasks without requiring parameter updates. This capabi…
EntroPIC: Towards Stable Long-Term Training of LLMs via Entropy Stabilization with Proportional-Integral Control
Kai Yang, Xin Xu, Yangkun Chen +5
Long-term training of large language models (LLMs) requires maintaining stable exploration to prevent the model from collapsing into sub-optimal behaviors. Entropy is crucial in th…
CausalMACE: Causality Empowered Multi-Agents in Minecraft Cooperative Tasks
Qi Chai, Zhang Zheng, Junlong Ren +3
Minecraft, as an open-world virtual interactive environment, has become a prominent platform for research on agent decision-making and execution. Existing works primarily adopt a s…
Learning Versatile Skills with Curriculum Masking
Yao Tang, Zhihui Xie, Zichuan Lin +2
Masked prediction has emerged as a promising pretraining paradigm in offline reinforcement learning (RL) due to its versatile masking schemes, enabling flexible inference across va…
Replay-enhanced Continual Reinforcement Learning
Tiantian Zhang, Kevin Zehua Shen, Zichuan Lin +4
Replaying past experiences has proven to be a highly effective approach for averting catastrophic forgetting in supervised continual learning. However, some crucial factors are sti…
Future-conditioned Unsupervised Pretraining for Decision Transformer
Zhihui Xie, Zichuan Lin, Deheng Ye +3
Recent research in offline reinforcement learning (RL) has demonstrated that return-conditioned supervised learning is a powerful paradigm for decision-making problems. While promi…
Sample Dropout: A Simple yet Effective Variance Reduction Technique in Deep Policy Optimization
Zichuan Lin, Xiapeng Wu, Mingfei Sun +4
Recent success in Deep Reinforcement Learning (DRL) methods has shown that policy optimization with respect to an off-policy distribution via importance sampling is effective for s…
A Survey on Transformers in Reinforcement Learning
Wenzhe Li, Hao Luo, Zichuan Lin +3
Transformer has been considered the dominating neural architecture in NLP and CV, mostly under supervised settings. Recently, a similar surge of using Transformers has appeared in…
Pretraining in Deep Reinforcement Learning: A Survey
Zhihui Xie, Zichuan Lin, Junyou Li +2
The past few years have seen rapid progress in combining reinforcement learning (RL) with deep learning. Various breakthroughs ranging from games to robotics have spurred the inter…
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…
Dynamics-Adaptive Continual Reinforcement Learning via Progressive Contextualization
Tiantian Zhang, Zichuan Lin, Yuxing Wang +7
A key challenge of continual reinforcement learning (CRL) in dynamic environments is to promptly adapt the RL agent's behavior as the environment changes over its lifetime, while m…
MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned
Anssi Kanervisto, Stephanie Milani, Karolis Ramanauskas +19
Reinforcement learning competitions advance the field by providing appropriate scope and support to develop solutions toward a specific problem. To promote the development of more…
JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning
Zichuan Lin, Junyou Li, Jianing Shi +3
Learning rational behaviors in open-world games like Minecraft remains to be challenging for Reinforcement Learning (RL) research due to the compound challenge of partial observabi…