Thomas R. Colin

Thomas R. Colin

E: thomas.colin (@)plymouth.ac.uk

T: 01752 600 600

A: Link 3, Plymouth University, Drake Circus, Plymouth PL4 8AA

 

Project: Developing creativity in cognitive robots

My project (#11) is about capturing and computationally reproducing some of the essential characteristics of creative cognition and insight. More precisely, I am interested in "thinking outside the box": the ability to depart radically from a tentative strategy in order to try something new. Developments in Reinforcement Learning, most notably Hierarchical approaches, have brought exciting new tools to tackle this problem at a very fundamental level of cognition.

Indeed, some Hierarchical Reinforcement Learning (HRL) agents can self-organize while interacting with their environment. They learn policies (strategies), structured hierarchically, which can direct their behaviour at different levels of abstraction. HRL agents learn not only by discovering a new sequence of elementary actions, but also by deciding between abstract strategies - from the "big picture" to precise motor control. This is expected to greatly reduce costly trial-and-error exploration, and to allow for quicker adjustment to new environments.

This is similar to animal and human behaviour. Natural agents with enough experience are adept at making radical changes between abstract policies - sometimes experiencing the illumination of a eureka-moment when the new big picture seems to hold unexpected promise. 

Background

I hold master’s degrees in Software Engineering (EFREI, France, 2008) and Cognitive Artificial Intelligence (Cum Laude, Utrecht University, The Netherlands, 2013). I have previously worked in Cognitive Modeling in the context of Urban Search and Rescue robots, with TNO Soesterberg and as part of the E.U. project "NIFTi". I also have experience as a software engineer (2008-2010, 2013-2014), and I have studied philosophy and cognitive psychology at Université Toulouse II-Le Mirail.