Intrinsic Motivation
intrinsic motivation
Max Garagnani
The project involves implementing a brain-realistic neurocomputational model able to exhibit the spontaneous emergence of cognitive function from a uniform neural substrate, as a result of unsupervised, biologically realistic learning. Specifically, it will focus on modelling the emergence of unexpected (i.e., non stimulus-driven) action decisions using neo-Hebbian reinforcement learning. The final deliverable will be an artificial brain-like cognitive architecture able to learn to act as humans do when driven by intrinsic motivation and spontaneous, exploratory behaviour.
Dr. Nicola Catenacci Volpi
This PhD project will push the boundaries of Continual Reinforcement Learning by investigating how agents can continuously learn and adapt over time, how they can autonomously develop and flexibly apply an ever-expanding repertoire of skills across various tasks, and what representations allow them to do this efficiently. The project aims to create AI systems that can sustain autonomous learning and adaptation in ever-changing environments with limited computational resources. The selected candidate will master and contribute to techniques in deep reinforcement learning, incorporating principles from probabilistic machine learning, such as information theory, intrinsic motivation, and open-ended learning frameworks. The project may use computer games as benchmarking tools or apply findings to robotic systems, including manipulators, intelligent autonomous vehicles, and humanoid robots.
A reward-learning framework of knowledge acquisition: How we can integrate the concepts of curiosity, interest, and intrinsic-extrinsic rewards
Recent years have seen a considerable surge of research on interest-based engagement, examining how and why people are engaged in activities without relying on extrinsic rewards. However, the field of inquiry has been somewhat segregated into three different research traditions which have been developed relatively independently -- research on curiosity, interest, and trait curiosity/interest. The current talk sets out an integrative perspective; the reward-learning framework of knowledge acquisition. This conceptual framework takes on the basic premise of existing reward-learning models of information seeking: that knowledge acquisition serves as an inherent reward, which reinforces people’s information-seeking behavior through a reward-learning process. However, the framework reveals how the knowledge-acquisition process is sustained and boosted over a long period of time in real-life settings, allowing us to integrate the different research traditions within reward-learning models. The framework also characterizes the knowledge-acquisition process with four distinct features that are not present in the reward-learning process with extrinsic rewards -- (1) cumulativeness, (2) selectivity, (3) vulnerability, and (4) under-appreciation. The talk describes some evidence from our lab supporting these claims.