63 citations · 212 across the 18 of their papers we have counts for
12 papers · 1 filter
Beyond the Dirac Delta: Mitigating Diversity Collapse in Reinforcement Fine-Tuning for Versatile Image Generation
Jinmei Liu, Haoru Li, Zhenhong Sun +6
Reinforcement learning (RL) has emerged as a powerful paradigm for fine-tuning large-scale generative models, such as diffusion and flow models, to align with complex human prefere…
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…
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…
Continual Offline Reinforcement Learning via Diffusion-based Dual Generative Replay
Jinmei Liu, Wenbin Li, Xiangyu Yue +3
We study continual offline reinforcement learning, a practical paradigm that facilitates forward transfer and mitigates catastrophic forgetting to tackle sequential offline tasks.…
Magnetic Field-Based Reward Shaping for Goal-Conditioned Reinforcement Learning
Hongyu Ding, Yuanze Tang, Qing Wu +3
Goal-conditioned reinforcement learning (RL) is an interesting extension of the traditional RL framework, where the dynamic environment and reward sparsity can cause conventional l…
MIXRTs: Toward Interpretable Multi-Agent Reinforcement Learning via Mixing Recurrent Soft Decision Trees
Zichuan Liu, Yuanyang Zhu, Zhi Wang +2
While achieving tremendous success in various fields, existing multi-agent reinforcement learning (MARL) with a black-box neural network makes decisions in an opaque manner that hi…
A Dirichlet Process Mixture of Robust Task Models for Scalable Lifelong Reinforcement Learning
Zhi Wang, Chunlin Chen, Daoyi Dong
While reinforcement learning (RL) algorithms are achieving state-of-the-art performance in various challenging tasks, they can easily encounter catastrophic forgetting or interfere…
Efficient Bayesian Policy Reuse with a Scalable Observation Model in Deep Reinforcement Learning
Jinmei Liu, Zhi Wang, Chunlin Chen +1
Bayesian policy reuse (BPR) is a general policy transfer framework for selecting a source policy from an offline library by inferring the task belief based on some observation sign…
Depthwise Convolution for Multi-Agent Communication with Enhanced Mean-Field Approximation
Donghan Xie, Zhi Wang, Chunlin Chen +1
Multi-agent settings remain a fundamental challenge in the reinforcement learning (RL) domain due to the partial observability and the lack of accurate real-time interactions acros…
Multitask Bandit Learning Through Heterogeneous Feedback Aggregation
Zhi Wang, Chicheng Zhang, Manish Kumar Singh +2
In many real-world applications, multiple agents seek to learn how to perform highly related yet slightly different tasks in an online bandit learning protocol. We formulate this p…
Instance Weighted Incremental Evolution Strategies for Reinforcement Learning in Dynamic Environments
Zhi Wang, Chunlin Chen, Daoyi Dong
Evolution strategies (ES), as a family of black-box optimization algorithms, recently emerge as a scalable alternative to reinforcement learning (RL) approaches such as Q-learning…
Lifelong Incremental Reinforcement Learning with Online Bayesian Inference
Zhi Wang, Chunlin Chen, Daoyi Dong
A central capability of a long-lived reinforcement learning (RL) agent is to incrementally adapt its behavior as its environment changes, and to incrementally build upon previous e…