Reinformed Dreamer: An Asymmetric World Model Efficiently Trained through Latent Guidance

By Gaspard Lambrechts · Paper · cs.LG

Much like humans benefit from guidance while learning, reinforcement learning algorithms may benefit from additional supervision beyond rewards. Leveraging additional information during training to learn better representations and behaviors has been the focus of asymmetric reinfo

Cs.lg

View original

HomeResourceLoading…