Timo Ewalds

Hmm, I just tried this. pysc2.bin.agent doesn't support pausing or controlling the speed, but pysc2.bin.play does for both --map and --replay. Does this match what you're seeing? Is it important...

The challenge here is the environment sends observations to render but doesn't go through the renderer's run loop. The renderer can't use the normal agent/env run loop since the renderer...

I haven't looked at the recent changes, but it's probably also worth renaming replay_actions.py to something more general like process_replays.py or similar. Also, thanks for adding documentation. If you have...

This is hard to fix given it's in the c++ api and in various bots.

It'd be great to have a C++ version of alphazero that uses TF2 and reverb. I didn't use reverb initially with the goal of maximizing what is doable on a...

That all sounds great! I was using tic-tac-toe as my basic test as it should learn that pretty quickly, then connect four as something a bit harder that it should...

Hah, I happened to be pulling in PRs for the first time in ages, and saw this comment. Thanks for the suggestion.

Merged in c464dea