Hands-On Machine Learning for Algorithmic Trading

Setting up the OpenAI environment

We will begin by instantiating and extracting key parameters from the LL environment:

env = gym.make('LunarLander-v2')state_dim = env.observation_space.shape[0] # number of dimensions in staten_actions = env.action_space.n # number of actionsmax_episode_steps = env.spec.max_episode_steps # max number of steps per episodeenv.seed(42)

We will also use the built-in wrappers that permit the periodic storing of videos that display the agent's performance:

from gym import wrappersenv = wrappers.Monitor(env,directory=monitor_path.as_posix(),video_callable=lambda count: count % video_freq == 0, force=True)

When running on a server or Docker container without a display, you can use pyvirtualdisplay.