Exploration vs. Exploitation – Learning the Optimal Reinforcement Learning Policy

Welcome back to this series on reinforcement learning! Last time, we left our discussion of Q-learning with the question of how an agent chooses to either explore the environment or to exploit it in order to select its actions. In this video, we’ll answer this…

Learning Dexterity

Watch Video We’ve trained a human-like robot hand to manipulate physical objects with unprecedented dexterity. Our system, called Dactyl, is trained entirely in simulation and transfers its knowledge to reality, adapting to real-world physics using techniques we’ve been working on for the past year. Dactyl…

13 Experts Weigh in on What We Should Teach Robots – AI Trends

Anca Dragan of UC Berkeley, left; Maria Bauza of MIT, center; Ashwin Dani of UConn, right We’ve reached a critical point in the development of robots. As robots become more and more common in our everyday lives, scientists and researchers are beginning to ask if we’re…

Fossil Friday Roundup: May 4, 2018 | PLOS Blogs Network

  Featured Image: Citipati osmolskae, IGM 100/1004 in left lateral view. Anterior is to the left. From Norell et al. (2018). Papers (All Open Access): Quantifying the living fossil concept (PalaeoE) Getting somewhere with the Red Queen: VISIT THE SOURCE ARTICLE Fossil Friday Roundup: May 4, 2018…