Compositional Learning of Visually-Grounded Concepts Using Reinforcement

arXiv:2309.04504v2 Announce Type: replace
Abstract: Children can rapidly generalize compositionally-constructed rules to unseen test sets. On the other hand, deep reinforcement learning (RL) agents need to be trained over millions of episodes, and their ability to generalize to unseen combinations remains unclear. Hence, we investigate the compositional abilities of RL agents, using the task of navigating to specified color-shape targets in synthetic 3D environments. First, we show that when RL agents are naively trained to navigate to target color-shape combinations, …

abstract agents arxiv children concepts cs.ai cs.lg episodes reinforcement reinforcement learning rules test type