This is a discussion channel for “World Model for Perception, Control and Language” by Prof. Yutaka Matsuo (The University of Tokyo). A link to the talk is the following. Please do not share the link to anyone outside of this slack workspace. Access Pass code can be found at the announcement channel. URL: https://vimeo.com/470866278 (22 minutes)
Thank you for your very interesting talk. Given the current success of RL in many domains, I'm curious how the presented approaches could be effective in the area of motor control which requires physical interactions with the real world. In particular, in robotics, generating human-like complex and dynamic behaviors in hardware robot using RL is still a significant challenge, and how we can learn from neuroscience.