Deep Reinforcement Learning to Master the Asymmetric Strategy of Baghchal

AI 中文解读

1. 核心亮点：用深度强化学习训练AI玩尼泊尔传统不对称棋类游戏Baghchal，发现MuZero算法能以86%的胜率碾压对手，展现了AI在复杂策略博弈中的顶尖水平。 2. 通俗解读：Baghchal就像老虎抓山羊——四只老虎要吃掉二十只山羊，山羊则要困住老虎。研究人员让四种AI算法（DQN、REINFORCE、PPO和MuZero）分别扮演老虎和山羊相互对战。结果MuZero表现最惊艳，因为它会像下棋高手一样提前模拟未来几十步的走法（通过蒙特卡洛树搜索），而PPO则像是个精打细算的务实派，虽然效果稍弱但计算成本低得多。其他两种算法要么容易走极端（比如DQN玩老虎时太贪心），要么不够稳定。 3. 实际影响：虽然这只是一款棋盘游戏，但它教会AI如何应对“不对称竞争”——比如商业谈判、资源分配甚至军事推演中，双方规则和优势截然不同。未来这类算法可以帮企业优化供应链、帮物流公司设计配送路线，甚至为棋类爱好者提供比人类更聪明的陪练。简单说，AI正在学会在不对等的条件下依然做出最优决策。

arXiv:2607.18296v1 Announce Type: new Abstract: Baghchal is a two-player asymmetric board game with Nepali origins where four tigers are to capture goats and twenty goats desire to keep tigers in immobility. Although Baghchal has a complex structure which is strategic, has perfect information structure, and has cultural meaning, it has not been adequately covered in deep reinforcement learning (RL) literature. This paper gives a systematic exploration of four deep RL solutions Deep Q-Network (DQN), REINFORCE, Proximal Policy Optimization (PPO) and MuZero that are trained on one side of the asymmetric gameplay of Baghchal and then evaluated on the other side. The algorithms are rated based on win rate, draw rate, average captures, training convergence and computational cost. It is experimentally found that MuZero generates the best performance in both tasks, achieving 86 percent win over these Tiger and 62 percent win over these Goat and the ability to do so is due to the model-based planning machine through the Monte Carlo Tree Search. PPO is the most realistic algorithm and is provided to be competitive over both asymmetric tasks with significantly reduced computational costs compared to MuZero. Emergent strategic behavior analysis shows that model-based strategies are optimal over long-horizon planning, whereas value-based counterparts like DQN are more biased up towards the Tiger role owing to the more substantial reward signal.