def _init():
env = environment(x,y,z,gamma, cutoffpenaltyscalar, rg_prob, turnspc, savepath)
env.seed(seed + rank)
return env
"""
def _init():
env = environment(x,y,z,gamma, cutoffpenaltyscalar, rg_prob, turnspc, savepath)
env.seed(seed + rank)
return env
set_global_seeds(seed)
return _init
if __name__ == '__main__':
num_cpu = 15 # Number of processes to use
# Create the vectorized environment
env = SubprocVecEnv([make_env(x,y,z, i) for i in range(num_cpu)])
eval_env=environment(x, y, z, gamma, cutoffpenaltyscalar, rg_prob, turnspc, savepath)
# Stable Baselines provides you with make_vec_env() helper
# which does exactly the previous steps for you:
# env = make_vec_env(env_id, n_envs=num_cpu, seed=0)
#create callbacks to record data, initiate events during training.
callbacklist=CallbackList([TimeLimit(episodetimesteps), EvalCallback(eval_env, log_path=savepath, n_eval_episodes=5
, deterministic=False, best_model_save_path=savepath)])
#create model with Stable Baselines package.
model = A2C(CnnPolicy, env, gamma=gamma, n_steps=updatesteps, learning_rate=LR, verbose=1)#, tensorboard_log=scenario)
model.learn(total_timesteps=episodetimesteps**50, callback=callbacklist) #total timesteps set to very large number so program will terminate based on runtime parameter)