We work on reinforcement learning (RL) methods to create autonomous agents that can efficiently solve complex tasks.
Bioinspired discovery of hierarchical subtasks
Inspired by recent discoveries in neuroscience, this work explores the use of feature specialization and clustering to decompose environments into a useful task subspace for hierarchical RL. See our ALA Workshop paper presenting our approach, named Specialized Neurons and Clustering (SNAC), for more details.
Adaptation in hierarchical RL
This work explores the benefits of using hierarchical architectures in RL for adaptation to new dynamics. The video shows an example of how our approach supports fast adaptation to new enemies in a game of capture-the-flag. See our ICRA paper for more details.