"""
def _init():
env = environment(x, y, z, gamma, turnspc, penaltyscalar, policyname)
env.seed(seed + rank)
return env
set_global_seeds(seed)
return _init
if __name__ == '__main__':
num_cpu = ncpu # 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=evalenv(x, y, z, gamma, turnspc, policyname)
env1 =environment(x, y, z, gamma, turnspc, penaltyscalar, policyname) #env annealreate/ numturns*eval_freq
# 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=evpath, n_eval_episodes=100, eval_freq=50000
, deterministic=False, best_model_save_path=evpath), EvalCallback(env1, log_path=savepath, n_eval_episodes=20, eval_freq=50000
, deterministic=False, best_model_save_path=savepath)])
if (os.path.exists("%s/best_model.zip" % savepath)):
# Instantiate the agent
model = A2C(policy, env, gamma=gamma, n_steps=episodetimesteps, learning_rate=LR, verbose=1, n_cpu_tf_sess=num_cpu)
# Load the trained agent
model = A2C.load("%s/best_model" % savepath, env=env)
def _init():
env = environment(x, y, z, gamma, turnspc, penaltyscalar, policyname)
env.seed(seed + rank)
return env
set_global_seeds(seed)
return _init
if __name__ == '__main__':
num_cpu = ncpu # 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 = evalenv(x, y, z, gamma, turnspc, penaltyscalar, policyname)
#env1 =environment(x, y, z, gamma, turnspc, policyname)
# 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=evpath,
n_eval_episodes=100,
eval_freq=50000,
deterministic=False,
best_model_save_path=evpath),
EvalCallback(env,
