Keras Deep Learning Cookbook

Training the agent

In this section, we look at how the agent is trained for EPISODES, improving the reward and recalculating the epsilon:

if __name__ == "__main__":    env = gym.make('CartPole-v1')    output_file = open("cartpole_v1_output.csv","w+")    state_size = env.observation_space.shape[0]    action_size = env.action_space.n    agent = DqnAgent(state_size, action_size)    # agent.load("./save/cartpole-dqn.h5")    done = False    batch_size = 32    count = 0    for e in range(EPISODES):        state = env.reset()        state = np.reshape(state, [1, state_size])        for time in range(500):            # env.render()            action = agent.act(state)            next_state, reward, done, _ = env.step(action)            reward = reward if not done else -10            next_state = np.reshape(next_state, [1, state_size]) agent.remember(state, ...