[WIP] PPO Example and RL Action Space Refactor

[bcollazo]

Inspired by #297. Looking to maybe reproduce and/or play some more with the hyperparameters.

This PR also refactors the "action space" code for RL approaches to auto-adjust depending on the map type (MINI vs BASE) and number of players playing (smaller maps and less players have a smaller spaces.Discrete box).

[netlify]

✅ Deploy Preview for catanatron-staging canceled.

Name	Link
🔨 Latest commit	769ebeb
🔍 Latest deploy log	https://app.netlify.com/projects/catanatron-staging/deploys/694899800ee6310008483f5b

[coveralls]

Pull Request Test Coverage Report for Build 20418703267

Details

• 62 of 65 (95.38%) changed or added relevant lines in 7 files are covered.
• 1 unchanged line in 1 file lost coverage.
• Overall coverage decreased (-0.1%) to 93.434%

---

Changes Missing Coverage	Covered Lines	Changed/Added Lines	%
catanatron/catanatron/gym/accumulators.py	11	12	91.67%
catanatron/catanatron/gym/envs/catanatron_env.py	20	22	90.91%

Files with Coverage Reduction	New Missed Lines	%
catanatron/catanatron/gym/accumulators.py	1	83.87%

Totals
Change from base Build 20200287589:	-0.1%
Covered Lines:	2974
Relevant Lines:	3183

---

💛 - Coveralls

[bcollazo]

Superseded by #343