Reinforcement learning offers a promising path towards the creation of intelligent agents, but state-of-the-art methods are woefully incapable when compared to even simple biological organisms. One of the reasons for this is the lack of object-based, compositional reasoning in deep-learning systems. In this project, we use the principle of object-oriented (i.e., relational) reasoning to design algorithms that learn and act more effectively.
QORA (Quantified Object Relation Aggregator) is a novel model-learning algorithm for reinforcement learning. More info coming soon; for now, check out the paper and other resources below. :)
Gabriel Stella, Dmitri Loguinov. ICML, July 2024.