In this section, we discuss the hyperbolic operations used in HNN formulations and set up the meta-learning problem. This particular setup is also known as the N-ways K-shot learning problem. This section provides the theoretical proofs of the theorems presented in our main paper. Note that points in the local tangent space follow Euclidean algebra. The columns present the number of tasks in each batch (# Tasks), HNN update learning rate (), meta update learning rate (), and size of hidden dimensions (d).

The pseudocode for Thought Cloning (TC) training framework is shown in Algorithm 1. Backpropagation Through Time was truncated at 20 steps in TC. Detailed hyperparameter settings are shown in Table 1. Figure 1 presents an example trajectory. For instance, the plan could be to "open the red door" Figure 3: Example trajectories of agents trained with different strategies. Because of the realization from being able to observe the agent's Attention is all you need.