Search Results for author: Sijia Xu

Found 3 papers, 1 papers with code

Diversity is Strength: Mastering Football Full Game with Interactive Reinforcement Learning of Multiple AIs

no code implementations28 Jun 2023 Chenglu Sun, Shuo Shen, Sijia Xu, Weidong Zhang

The AI's strength is closely related to its diversity of strategies, and this relationship can guide us to train AI with both strong and rich strategies.

Mastering Asymmetrical Multiplayer Game with Multi-Agent Asymmetric-Evolution Reinforcement Learning

no code implementations20 Apr 2023 Chenglu Sun, Yichi Zhang, Yu Zhang, Ziling Lu, Jingbin Liu, Sijia Xu, Weidong Zhang

We propose asymmetric-evolution training (AET), a novel multi-agent reinforcement learning framework that can train multiple kinds of agents simultaneously in AMP game.

Multi-agent Reinforcement Learning reinforcement-learning

Macro action selection with deep reinforcement learning in StarCraft

1 code implementation2 Dec 2018 Sijia Xu, Hongyu Kuang, Zhi Zhuang, Renjie Hu, Yang Liu, Huyang Sun

These rules are not scalable and efficient enough to cope with the enormous yet partially observed state space in the game.

reinforcement-learning Reinforcement Learning (RL) +1

Cannot find the paper you are looking for? You can Submit a new open access paper.