Reproduce Gridnet's SOTA agent with Trueskill Evaluation

Now that we are trying to get the self-play agent working, it's important to set baselines that we want to achieve and excel. Our best past experiment is [this](https://wandb.ai/vwxyzjn/gym-microrts-paper/runs/asrpz468) (which I just now realized Chris had run with `--num-bot-envs 48`), which can achieve a Trueskill of `35.55` ([source](https://wandb.ai/vwxyzjn/cleanrl/runs/2x90jbfo)).


I am going to try reproduce with `python ppo_gridnet.py --num-bot-envs 24 --num-selfplay-envs 0 --total-timesteps 100000000 --num-models 300`, see if we can get the same level of performance, so

```
python ppo_gridnet.py \
--num-bot-envs 24 --num-selfplay-envs 0 \
--total-timesteps 100000000 --num-models 300 \
--capture-video --prod-mode
```

After this, I am going to check if I can reproduce the same results with the new vecenv implementation in #34