9 papers
When Context Returns: Toward Robust Internalization in On-Policy Distillation
Xun Wang, Ruishuo Chen, Zhuoran Li +2
Recent work has shown that on-policy distillation can internalize privileged context, such as system prompts or task hints, into a student model so that the context is no longer ne…
Diffusing to Coordinate: Efficient Online Multi-Agent Diffusion Policies
Zhuoran Li, Hai Zhong, Xun Wang +3
Online Multi-Agent Reinforcement Learning (MARL) is a prominent framework for efficient agent coordination. Crucially, enhancing policy expressiveness is pivotal for achieving supe…
Beyond the Proxy: Trajectory-Distilled Guidance for Offline GFlowNet Training
Ruishuo Chen, Xun Wang, Rui Hu +2
Generative Flow Networks (GFlowNets) excel at sampling diverse, high-reward objects. In many practical applications where active reward queries are infeasible, these models must be…
Offline-to-Online Multi-Agent Reinforcement Learning with Offline Value Function Memory and Sequential Exploration
Hai Zhong, Xun Wang, Zhuoran Li +1
Offline-to-Online Reinforcement Learning has emerged as a powerful paradigm, leveraging offline data for initialization and online fine-tuning to enhance both sample efficiency and…
OM2P: Offline Multi-Agent Mean-Flow Policy
Zhuoran Li, Xun Wang, Hai Zhong +3
Generative models, especially diffusion and flow-based models, have been promising in offline multi-agent reinforcement learning. However, integrating powerful generative models in…
Reparameterization Proximal Policy Optimization
Hai Zhong, Xun Wang, Zhuoran Li +1
By leveraging differentiable dynamics, Reparameterization Policy Gradient (RPG) achieves high sample efficiency. However, current approaches are hindered by two critical limitation…