diff --git a/requirements.txt b/requirements.txt index 4c5715b87594f62e3412502d31c3145c3820129c..a1a032907bdbe4bbdabbd4697a482298d88edd46 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,3 +1,6 @@ gym -stable-baselines -tensorflow==1.15 +stable-baselines3 +optuna +opencv-python +sklearn +# tensorflow==1.15 diff --git a/sandbox/multicolumn/run_dual_ppo.py b/sandbox/multicolumn/run_dual_ppo.py index aade75f817918eab9c7b081993efd5c27b50cb3e..6639017a87a0370077c787a928e22e6737510c7a 100644 --- a/sandbox/multicolumn/run_dual_ppo.py +++ b/sandbox/multicolumn/run_dual_ppo.py @@ -1,8 +1,13 @@ +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