Current progress & Near‐term plan

Current progress

• This version uses CNN based representation network + LSTM based dynamics network architecture for RGB input environment (LunarLander-v2, using rgb states wrapped by PixelObservationWrapper(self.env))
• It works for randomly initialized env(random terrain and acceleration), but still not perfectly converge to more than 200 score. It needs to be improved further.

Near-term plan

• (Near-term plan) Test stronger encoder architecture
• (Near-term plan) Efficiency optimization about code and nni experiment setting
• (Near-term plan) Try to use off-policy correction method like V-trace, Retrace.

Previous

Progress

• contents