Guojun Xie — accepted AI-conference papers

2025

Acting Beyond Learning: Imagination-Assisted Decision-Making in the Visual-based Multi-Agent Cooperative Scenarios

Huanhuan Yang, Dianxi Shi, Songchang Jin, Guojun Xie, Yang Chen, Chunping Qiu +1

AAAI 2025technical

Learning optimal policies in multi-agent cooperative settings with visual observations is significant and challenging. Agents must first perform state representation learning for their image observations and then learn policies in the abstracted state space. Aiming at this problem, we propose a nove…

Cited by 0 Source ↗PDF ↗Scholar ↗

2022

Self-supervised representations for multi-view reinforcement learning

Huanhuan Yang, Dianxi Shi, Guojun Xie, Yingxuan Peng, Yi Zhang, Yantai Yang +1

UAI 2022poster

Learning policies from raw, pixel images are quite important for the real-world application of deep reinforcement learning (RL). Standard model-free RL algorithms focus on single-view settings and unify the representation learning and policy learning into an end-to-end training process. However, suc…

Cited by 7 Source ↗PDF ↗code ↗Scholar ↗