We work on reinforcement learning (RL) methods to create autonomous agents that can efficiently solve complex tasks.

Bioinspired discovery of hierarchical subtasks

Value maps for two learned sub-policies. The object-based option is learned using features specialized to focus on dynamic objects - it appears to have the blue agent prevent the enemy agent (E) from reaching the blue flag (blue star). The spatial-based option is learning using spatial features and is independent of the enemy.

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.