Why is my `rllib.models.torch.torch_modelv2.TorchModelV2` receiving a Tensor of shape ( 32, <observation size> )?

[mannyv]

Hi @MrDracoG,

Welcome to the forum.

This post may have the information you are looking for.

Yet another question on RNN sequencing

Hi @mg64ve There are 3 (sometimes 4) distinct phases that the model is called in. Your debugging has revealed 2 of them. These 3 are from the initialization phase. The y are taken from a dummy batch of all zeros. I ignore these unless they are generatimg an error. torch.Size([32, 1, 2]) torch.Size([1, 1, 2]) torch.Size([4, 8, 2]) These are from the rollout phase when compute actions is called to sanple new trajectories from the environment. Your config has 20 envs per worker each of which i…