Train_PPO Namespace Reference

Variables
	ppo_path = os.path.join('Training', 'Saved Models', f'Drone_PPO_Model_{datetime.datetime.now().strftime("%Y_%m_%d_%H_%M_%S")}')
	log_path = os.path.join('Training', 'Logs')
int	episodes = 100
	env = DroneRobot()
	debugMode
int	timesteps = env.steps_per_episode * episodes
	model = PPO('MlpPolicy', env, verbose=1, tensorboard_log=log_path, device='cpu', ent_coef=10, learning_rate=0.0001)
	total_timesteps

Variable Documentation

debugMode

Train_PPO.debugMode

Definition at line 17 of file Train_PPO.py.

env

Train_PPO.env = DroneRobot()

Definition at line 16 of file Train_PPO.py.

episodes

int Train_PPO.episodes = 100

Definition at line 13 of file Train_PPO.py.

log_path

Train_PPO.log_path = os.path.join('Training', 'Logs')

Definition at line 10 of file Train_PPO.py.

model

Train_PPO.model = PPO('MlpPolicy', env, verbose=1, tensorboard_log=log_path, device='cpu', ent_coef=10, learning_rate=0.0001)

Definition at line 27 of file Train_PPO.py.

ppo_path

Train_PPO.ppo_path = os.path.join('Training', 'Saved Models', f'Drone_PPO_Model_{datetime.datetime.now().strftime("%Y_%m_%d_%H_%M_%S")}')

Definition at line 8 of file Train_PPO.py.

timesteps

int Train_PPO.timesteps = env.steps_per_episode * episodes

Definition at line 21 of file Train_PPO.py.

total_timesteps

Train_PPO.total_timesteps

Definition at line 36 of file Train_PPO.py.