The representation dimension in the code is inconsistent with the paper

[zhang1999]

Hello! I noticed that the representation dim of some models (such as ICM) is 512 in Table 3. However, in the code, the representation of these models are 39200. When I use these models, should I add a linear layer after the conv layers to project the representation to 512 dim?

[roger-creus]

this issue is right. Is it intentioned to have a hidden dim of 39200 for the pixel encoder in DDPG?