script+cnn.py

obs = env_script.reset()
done = False

# 1. Get wood with the CNN
for i in tqdm(range(3000)):
    obs = torch.from_numpy(obs['pov'].transpose(2, 0, 1)[None].astype(np.float32) / 255).cuda()
    probabilities = torch.softmax(model(obs), dim=1)[0].detach().cpu().numpy()
    action = np.random.choice(action_list, p=probabilities)
    obs, reward, done, _ = env_script.step(action)

# 2. Craft stone pickaxe with scripted actions
for action in tqdm(script):
    obs, reward, done, _ = env_cnn.step(str_to_act(env_cnn, action))

env_cnn.release()
env_cnn.play()