Steven Lin

reinforcement learning (2) goal-conditioned policy (2) self-supervised learning (2) visual reinforcement learning (1) robot learning (1) unsupervised representation learning (1) latent variable model (1) skill learning (1) image observation (1) self-supervised reinforcement learning (1) goal-reaching policy (1) state coverage (1) maximum-entropy goal distribution (1) skill repertoire (1) representation learning (1) goal relabeling (1) sample efficiency (1) sequential decision making (1)