Agent performing random actions around the environment

Art057_Python_004.py

# Reset environment to initial state
state, info = env.reset()
# Cycle through 30 random steps redering and displaying the agent inside the environment each time
for _ in range(30):
    
    # Render and display current state of the environment
    plt.imshow(env.render()) # render current state and pass to pyplot
    plt.axis('off')
    display.display(plt.gcf()) # get current figure and display
    display.clear_output(wait=True) # clear output before showing the next frame
    
    # Sample a random action from the entire action space
    random_action = env.action_space.sample()
    
    # Pass the random action into the step function
    state, reward, done, _, info = env.step(random_action)
    
    # Reset environment when done=True, i.e., when the agent falls into a Hole (H) or reaches the Goal (G)
    if done:
        # Render and display current state of the environment
        plt.imshow(env.render()) # render current state and pass to pyplot
        plt.axis('off')
        display.display(plt.gcf()) # get current figure and display
        display.clear_output(wait=True) # clear output before showing the next frame
        # Reset environment
        state, info = env.reset()

# Close environment 
env.close()