Jake Grigsby

Results 3 issues of Jake Grigsby

This is basically #214 with most of the extra features cut out, because the PER bug needs to get fixed, whether or not the rest ever merges. DQfD, NoisyNets, and...

enhancement

I've been trying to set up a multiworker Rainbow DQN baseline for procgen, similar to what's described in [Leveraging Procedural Generation for Benchmarking Reinforcement Learning](https://arxiv.org/abs/1912.01588). This is roughly how I'm...

It seems like Gen 1 compatibility isn't a huge focus, but by creating matchups between random `Player` baselines from ~1k gen1ou teams I've encountered a few issues which seem fixable....