相关实验视频
Updated: Sep 10, 2025

Trajectory Data Analyses for Pedestrian Space-time Activity Study
Published on: February 25, 2013
通过推断低维潜态,在连续空间中进行动态规划和信息获取
Takazumi Matsumoto1, Kentaro Fujii2, Shingo Murata2
1Cognitive Neurorobotics Research Unit, Okinawa Institute of Science and Technology, Okinawa 904-0495, Japan.
EFE-GLean通过整合认识价值来提高信息搜索行为来增强主动推断. 通过利用隐藏的信息和适应环境变化来实现目标.
科学领域:
- 认知科学
- 计算神经科学
- 人工智能
背景情况:
- 积极推断为目标导向和认识行为提供了统一的框架.
- 在高维的连续行动空间中实施政策搜索带来了可扩展性和稳定性的挑战.
- 之前的T-GLean模型允许有效的目标导向规划,但缺乏信息搜索的认识价值.
研究的目的:
- 介绍EFE-GLean,这是T-GLean的延伸,将认识价值纳入规划.
- 让代理人参与寻找信息的行为,这对于实现预期的结果至关重要.
- 通过低维轨迹推断和信息获取最大化来证明增强目标导向的政策.
主要方法:
- 通过将一个认识学术术语整合到预期的自由能量最小化过程中,开发了EFE-GLean.
- 在离散和连续领域的扩展T迷宫任务上使用模拟实验.
- 在适应性规划中同时最小化过去的变量自由能量和未来的预期自由能量.
主要成果:
- 通过利用隐藏的环境信息,EFE-GLean的代理人成功实现了目标.
- 通过动态修改计划,该模型展示了适应环境突然变化的能力.
- 模拟实验证实了代理人对目标指导和信息搜索行为的能力.
结论:
- EFE-GLean有效地将认识价值整合到积极的推断中,以增强代理行为.
- 该模型为复杂环境中的政策搜索提供了可扩展和稳定的方法.
- EFE-GLean提供了对适应性目标导向和认识的行动背后的机制的见解.
更多相关视频
10:44Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline
Published on: December 7, 2021
11:54Real-Time Proxy-Control of Re-Parameterized Peripheral Signals using a Close-Loop Interface
Published on: May 8, 2021
相关概念视频
Statically Indeterminate Problem Solving
Inductive Reasoning
Inductive reasoning is common in descriptive science. A life scientist makes observations and records them. This data can be qualitative or...
Schemas
State Space Representation
Consider an RLC circuit, a...
Collisions in Multiple Dimensions: Problem Solving
A small car of mass 1,200 kg traveling east at 60 km/h collides at an intersection with a truck of mass 3,000 kg traveling due north at 40 km/h. The two vehicles are locked together. What is the...
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...