Modeling the Physical World: Perception, Learning, and Control
NeurIPS Workshop, December 7, 2018, Montreal, Canada
- 08:40 - 09:00: Josh Tenenbaum: Opening Remark
- 09:00 - 09:30: Zico Kolter: Differentiable Physics and Control
- 09:30 - 10:00: Emo Todorov: Physics-Based Control
- 10:00 - 10:10: Oral: ChainQueen: A Real-Time Differentiable Physical Simulator for Soft Robotics
- 10:10 - 10:20: Oral: To Stir or Not to Stir: Online Estimation of Liquid Properties for Pouring Actions
- 10:20 - 10:30: Oral: Learning Robotic Manipulation through Visual Planning and Acting
10:30 - 11:00: (Coffee / Posters)
- 11:00 - 11:30: Jitendra Malik: Linking Perception and Action
- 11:30 - 12:00: Chelsea Finn: An agent that can do many things (by modeling the world)
12:00 - 14:00: (Lunch / Posters)
- 14:00 - 14:30: Peter Battaglia: Structure in Physical Intelligence
- 14:30 - 15:00: Dan Yamins: The Objects of Our Curiosity: Intrinsic Motivation, Intuitive Physics and Self-Supervised Learning
15:00 - 15:30: (Coffee / Posters)
- 15:30 - 16:00: Jeannette Bohg: On perceptual representations and how they interact with actions and physical models
- 16:00 - 16:30: Leslie Kaelbling: Learning models of very large hybrid domains
- 16:30 - 17:00: Marc Toussaint: Models & Abstractions for Physical Reasoning
- 17:00 - 18:00: Panel Discussion