Manuel Lopes
INRIA, Bordeaux

Exploration Biases for Task Learning In Machines and Animals

Tuesday 17th of November 2015 at 12:00pm
560 Evans

Curiosity is very predominant in people and many animals, but its mechanisms are poorly understood. Motivated by research on neuroscience and child development we want to develop methods to understand those mechanims and provide machines with adaptation capabilities similar to the ones of animals. Our model includes exploration biases such as reward, information, learning progress and reward antecipation. We show that only the combination those biases can explain the observed empirical data. We also show how exploration biases based on learning progress can improve robustness to lack of knowledge about a domain and its robustness to environmental changes.
(video)

Join Email List

You can subscribe to our weekly seminar email list by sending an email to majordomo@lists.berkeley.edu that contains the words subscribe redwood in the body of the message.
(Note: The subject line can be arbitrary and will be ignored)