Evaluate agent by visualizing its actions

Art057_Python_012.py

# Reset environment to initial state
state, info = env.reset()

# Cycle through 50 steps redering and displaying environment state each time
for _ in range(50):
    
    # 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
    
    # Use greedy policy to evaluate
    action = eval_greedy(Qtable, state)
    
    # Pass action into step function
    state, reward, done, _, info = env.step(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 final 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
        state, info = env.reset()

env.close()