Jarno Seppänen
@nanrecip.es
Savorer of NaN – machine learning, data, code – here for the preprints – research scientist at NVIDIA, ex-Supercell, ex-Nokia – opinions mine
Feels like a failure mode of RL training - ”get a +1 reward if the tests pass”
March 24, 2025 at 5:20 PM
Feels like a failure mode of RL training - ”get a +1 reward if the tests pass”
Plotly Express works for me, simple to do quick plots plus they’re interactive/zoomable
November 29, 2024 at 7:35 AM
Plotly Express works for me, simple to do quick plots plus they’re interactive/zoomable
