To do

• Create training algorithm of competing policies and select 'winner' after each iteration. Competing policies have different environment configs. Goal: optimize environment parameters more efficiently and automaticly at run time rather than manually after full (10 hour) experiments.

• Fix link in https://github.com/doesburg11/PredPreyGrass/tree/main/src/predpreygrass/rllib/v1_0. Create .md for reward scaling from legacy website.