基于消息传递的自回归主动推理智能体，通过预测不确定性调节动作。
Message passing-based inference in an autoregressive active inference agent
- 在因子图上用消息传递实现自回归主动推理
- 动作受预测不确定性调节，抵达时间较晚但动态模型更准
- 适合需平衡探索与利用的连续控制任务
我们设计了一种基于因子图上消息传递的自回归主动推理智能体。预期自由能被推导并分布于规划图中。该智能体在机器人导航任务中得到验证，展示了在连续观测空间和有界连续动作空间下的探索与利用能力。相比经典最优控制器，该智能体根据预测不确定性调节动作，虽抵达时间较晚，但对机器人动力学的建模更为准确。
原文摘要 · Abstract (English)
We present the design of an autoregressive active inference agent in the form of message passing on a factor graph. Expected free energy is derived and distributed across a planning graph. The proposed agent is validated on a robot navigation task, demonstrating exploration and exploitation in a continuous-valued observation space with bounded continuous-valued actions. Compared to a classical optimal controller, the agent modulates action based on predictive uncertainty, arriving later but with a better model of the robot's dynamics.
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。