Renzhe Zhou

contrastive learning (1) offline reinforcement learning (1) model-based learning (1) state transition (1) variational autoencoder (1) uncertainty estimation (1) offline meta-reinforcement learning (1) encoder-decoder architecture (1) bellman update (1) task representation learning (1) state transition reconstruction (1) task auto-encoder (1) pseudo-transition construction (1) weighted policy optimization (1)