151 citations · 276 across the 14 of their papers we have counts for
14 papers
Offline Meta Reinforcement Learning with In-Distribution Online Adaptation
Jianhao Wang, Jin Zhang, Haozhe Jiang +3
Recent offline meta-reinforcement learning (meta-RL) methods typically utilize task-dependent behavior policies (e.g., training RL agents on each individual task) to collect a mult…
Towards Global Optimality in Cooperative MARL with the Transformation And Distillation Framework
Jianing Ye, Chenghao Li, Yongqiang Dou +3
Decentralized execution is one core demand in multi-agent reinforcement learning (MARL). Recently, most popular MARL algorithms have adopted decentralized policies to enable decent…
Latent-Variable Advantage-Weighted Policy Optimization for Offline RL
Xi Chen, Ali Ghadirzadeh, Tianhe Yu +6
Offline reinforcement learning methods hold the promise of learning policies from pre-collected datasets without the need to query the environment for new transitions. This setting…
Self-Organized Polynomial-Time Coordination Graphs
Qianlan Yang, Weijun Dong, Zhizhou Ren +3
Coordination graph is a promising approach to model agent collaboration in multi-agent reinforcement learning. It conducts a graph-based value factorization and induces explicit co…
Episodic Multi-agent Reinforcement Learning with Curiosity-Driven Exploration
Lulu Zheng, Jiarui Chen, Jianhao Wang +6
Efficient exploration in deep cooperative multi-agent reinforcement learning (MARL) still remains challenging in complex coordination problems. In this paper, we introduce a novel…
Offline Reinforcement Learning with Reverse Model-based Imagination
Jianhao Wang, Wenzhe Li, Haozhe Jiang +3
In offline reinforcement learning (offline RL), one of the main challenges is to deal with the distributional shift between the learning policy and the given dataset. To address th…
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…
Active Hierarchical Exploration with Stable Subgoal Representation Learning
Siyuan Li, Jin Zhang, Jianhao Wang +2
Goal-conditioned hierarchical reinforcement learning (GCHRL) provides a promising approach to solving long-horizon tasks. Recently, its success has been extended to more general se…
QPLEX: Duplex Dueling Multi-Agent Q-Learning
Jianhao Wang, Zhizhou Ren, Terry Liu +2
We explore value-based multi-agent reinforcement learning (MARL) in the popular paradigm of centralized training with decentralized execution (CTDE). CTDE has an important concept,…
MetaCURE: Meta Reinforcement Learning with Empowerment-Driven Exploration
Jin Zhang, Jianhao Wang, Hao Hu +4
Meta reinforcement learning (meta-RL) extracts knowledge from previous tasks and achieves fast adaptation to new tasks. Despite recent progress, efficient exploration in meta-RL re…
Towards Understanding Cooperative Multi-Agent Q-Learning with Value Factorization
Jianhao Wang, Zhizhou Ren, Beining Han +2
Value factorization is a popular and promising approach to scaling up multi-agent reinforcement learning in cooperative settings, which balances the learning scalability and the re…
Influence-Based Multi-Agent Exploration
Tonghan Wang, Jianhao Wang, Yi Wu +1
Intrinsically motivated reinforcement learning aims to address the exploration challenge for sparse-reward tasks. However, the study of exploration methods in transition-dependent…
Learning Nearly Decomposable Value Functions Via Communication Minimization
Tonghan Wang, Jianhao Wang, Chongyi Zheng +1
Reinforcement learning encounters major challenges in multi-agent settings, such as scalability and non-stationarity. Recently, value function factorization learning emerges as a p…
Object-Oriented Dynamics Learning through Multi-Level Abstraction
Guangxiang Zhu, Jianhao Wang, Zhizhou Ren +2
Object-based approaches for learning action-conditioned dynamics has demonstrated promise for generalization and interpretability. However, existing approaches suffer from structur…