got the dual ppo working, with some of the classes for optuna tuning"

requirements.txt

 gym
-stable-baselines
-tensorflow==1.15
+stable-baselines3
+optuna
+opencv-python
+sklearn
+# tensorflow==1.15

sandbox/multicolumn/run_dual_ppo.py

+from typing import Dict
+from typing import Any
 import numpy as np
 import gym
 from stable_baselines3 import PPO
 from stable_baselines3.ppo import MlpPolicy
 from stable_baselines3.common.env_util import make_vec_env
+from stable_baselines3.common.callbacks import EvalCallback
+from stable_baselines3.common.vec_env import VecEnv
+import optuna
 
 from tutorenvs.utils import MultiDiscreteToDiscreteWrapper