Matheus M. Centa

icon indicating a website link linkedin.com/in/mmcenta/

icon location Lille, France icon location PhD Candidate in Reinforcement Learning @ Inria/CNRS/Univ. Lille Passionate about AI research.

Results 12 comments of Matheus M. Centa
trafficstars

Fix -inconsistency of layers/net_arch usage in cnn policy between different algorithms

I can come up with three reasons for the change: - **Uniformity**: as I was working with a recent project, I used the [Custom Policy](https://stable-baselines.readthedocs.io/en/master/guide/custom_policy.html) documentation page as a reference....

Option to use pre-trained embeddings as initializers

I don't think I understand your question 😅 What I mean by using pre-trained embeddings is that the context vectors are initialized to a set of pre-defined embeddings given by...