[2M4-OS-19b] 世界モデルと知能(2/4)

[2M4-OS-19b-01] A Study on Training PID Controllable World Models

〇Masaya Kageyama¹, Masashi Okada¹, Tadahiro Taniguchi^2,1 (1. Panasonic Corp., 2. Ritsumeikan Univ.)

Keywords:world model, representation learning, control theory

World models will be an effective paradigm that enables control systems in partially observable environments, e.g., visual servoing. However, the previous literature represents controllers by neural policies, and it makes it difficult to apply to industrial scenarios with several strict requirements such as realtime control and behaviors’ explainability. This paper aims to obtain world models in which we can utilize PID controllers, a well-established and time-tested scheme in the industry. For this purpose, we introduce a new loss function and heuristics to previous world model method methods, Recurrent State Space Model and Dreaming, and discuss how to realize PID controllable world modes through visualization analysis and control experiments in learned world models.