Applying DQN to a game

So far, we have randomly picked an action and applied it to the game. Now, let's apply DQN for selecting actions for playing the PacMan game.

1. We define the q_nn policy function as follows:

def policy_q_nn(obs, env):
    # Exploration strategy - Select a random action
    if np.random.random() < explore_rate:
        action = env.action_space.sample()
    # Exploitation strategy - Select the action with the highest q
    else:
        action = np.argmax(q_nn.predict(np.array([obs])))
    return action

2. Next, we modify the episode function to incorporate calculation of q_values and train the neural network on the sampled experience buffer. This is shown in the following code:

def episode(env, policy, r_max=0, t_max=0):

    # create the empty list to contain game memory
    #memory = deque(maxlen=1000)
    
    # observe initial state
  ...