Michael Laskin

contrastive learning (3) reinforcement learning (3) off-policy learning (2) deep reinforcement learning (2) representation learning (2) exploration-exploitation tradeoff (1) mutual information (1) skill discovery (1) off-policy reinforcement learning (1) human feedback (1) generative model (1) upper confidence bound (1) ensemble method (1) uncertainty estimation (1) intrinsic reward (1) unsupervised reinforcement learning (1) unsupervised representation (1) behavioral diversity (1) convolutional encoder (1) off-policy control (1)