用物体级表示+树搜索，让智能体更懂复杂环境中的物体互动。
Object-Centric World Models Meet Monte Carlo Tree Search
- 用图神经网络建模物体间交互关系，实现物体级环境理解。
- 在多物体交互场景中成功训练，能准确预测动态变化。
- 适合研究模型化强化学习、物体级表示与规划融合的读者。
本文提出ObjectZero，一种新型强化学习算法，利用物体级表征提升对动态环境的建模能力。不同于传统方法将世界视为单一输入，该方法采用图神经网络（GNN）捕捉多个物体间的复杂交互。这些可操作且相互作用的物体构成模型对环境理解的基础。我们在一个包含多种互动物体的复杂环境中训练该算法，证明其能有效学习并预测物体动态。结果表明，基于物体中心表征的结构化世界模型可成功融入以蒙特卡洛树搜索（MCTS）为规划模块的模型基强化学习框架中。
原文摘要 · Abstract (English)
In this paper, we introduce ObjectZero, a novel reinforcement learning (RL) algorithm that leverages the power of object-level representations to model dynamic environments more effectively. Unlike traditional approaches that process the world as a single undifferentiated input, our method employs Graph Neural Networks (GNNs) to capture intricate interactions among multiple objects. These objects, which can be manipulated and interact with each other, serve as the foundation for our model's understanding of the environment. We trained the algorithm in a complex setting teeming with diverse, interactive objects, demonstrating its ability to effectively learn and predict object dynamics. Our results highlight that a structured world model operating on object-centric representations can be successfully integrated into a model-based RL algorithm utilizing Monte Carlo Tree Search as a planning module.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。