UC Berkeley and Google AI Researchers Introduce ‘Director’: a Reinforcement Learning Agent that Learns Hierarchical Behaviors from Pixels by Planning in the Latent Space of a Learned World Model

UC Berkeley and Google AI Researchers Introduce ‘Director’: a Reinforcement Learning Agent that Learns Hierarchical Behaviors from Pixels by Planning in the Latent Space of a Learned World Model. The world model Director builds from pixels allows effective planning in a latent space. To anticipate future model states given future actions, the world model first … Continue reading UC Berkeley and Google AI Researchers Introduce ‘Director’: a Reinforcement Learning Agent that Learns Hierarchical Behaviors from Pixels by Planning in the Latent Space of a Learned World Model