-
Hw1: Meta Learning on Omniglot
Dataset organization, training,
-
Hw2:
-
Hw3: Goal Conditioned Reinforcement Learning & Hindsight Experience Replay
Simple RL agent + task id on two environment: Flip bits and
Hw1: Meta Learning on Omniglot
Dataset organization, training,
Hw2:
Hw3: Goal Conditioned Reinforcement Learning & Hindsight Experience Replay
Simple RL agent + task id on two environment: Flip bits and