PositionWe are looking for an enthusiastic PhD-TA candidate to work on advancing the field of sequential decision making under partial observations, with a particular focus on safe reinforcement learning methodologies. The primary objective is to build AI agents that, given a limited number of sensors, can operate safely in an unknown environment. The project focuses on the development of novel methods that can learn models of the world dedicated to safety. Such a model may be built based on the experiences of the agent or historical data collected by a different agent.
ProgramDuring your PhD, you will have the opportunity to tackle challenging problems related to the use of memory, feature extraction, and representation learning. You will delve deeply into the rapidly evolving field of reinforcement learning, while also exploring relevant areas of machine learning.
GroupYou will work on the Data and AI cluster, where you will have the chance to collaborate with experts designing new AI methods, algorithms and tools to expand the reach of AI and its generalization abilities, focusing particularly on the foundational issues of robustness and safety. The cluster offers a inclusive and collaborative workspace with numerous opportunities for social interactions.
Application and Supervision The position is available from December 1st and will be performed under the supervision of Dr. Thiago D. Simão (
httpss://tdsimao.github.io).