Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Critics

arXiv:2403.09930v1 Announce Type: new
Abstract: A key aspect of intelligence is the ability to demonstrate a broad spectrum of behaviors for adapting to unexpected situations. Over the past decade, advancements in deep reinforcement learning have led to groundbreaking achievements to solve complex continuous control tasks. However, most approaches return only one solution specialized for a specific problem. We introduce Quality-Diversity Actor-Critic (QDAC), an off-policy actor-critic deep reinforcement learning algorithm that leverages a value function critic and a successor features critic …

actor actor-critic arxiv cs.ai cs.lg diverse diversity features quality type value via