We want to minimize the ddpg training time. For a first optimization pass, line_profiler-level profiling would be most appropriate. My guess is most of the time is being spent in the dynamics metrics, and there's lots of opportunities for speedups there since that class does a lot of costly numpy transfers.
Here is the invocation of interest:
We want to minimize the ddpg training time. For a first optimization pass,
line_profiler
-level profiling would be most appropriate. My guess is most of the time is being spent in the dynamics metrics, and there's lots of opportunities for speedups there since that class does a lot of costly numpy transfers.