Language as a Cognitive Tool to Imagine Goals in Curiosity-Driven Exploration

Posted by klaurent MIT

Kavli Affiliate: Peter Ford | First 5 Authors: Cédric Colas, Tristan Karch, Nicolas Lair, Jean-Michel Dussoux, Clément Moulin-Frier | Summary: Developmental machine learning studies how artificial agents can model the way children learn open-ended repertoires of skills. Such agents need to create and represent goals, select which ones to pursue and learn to achieve them. […]


Continue.. Language as a Cognitive Tool to Imagine Goals in Curiosity-Driven Exploration

On the Search for Feedback in Reinforcement Learning

Posted by klaurent Peking

Kavli Affiliate: Ran Wang | First 5 Authors: Ran Wang, Karthikeya S. Parunandi, Aayushman Sharma, Raman Goyal, Suman Chakravorty | Summary: The problem of Reinforcement Learning (RL) in an unknown nonlinear dynamical system is equivalent to the search for an optimal feedback law utilizing the simulations/ rollouts of the dynamical system. Most RL techniques search […]


Continue.. On the Search for Feedback in Reinforcement Learning