Qiming Zou

Sample-Efficient Goal-Conditioned Reinforcement Learning via Predictive Information Bottleneck for Goal Representation Learning

We propose Predictive Information bottleneck for Goal representation learning (PI-Goal), a self-supervised method for sample-efficient goal-conditioned reinforcement learning (RL). Goal-conditioned RL learns to reach commanded goals with reward signals. A goal could be given in a noisy or abstract f…