| def __init__(self, enviroment, optimizer): | |
| # Initialize atributes | |
| self._state_size = enviroment.observation_space.n | |
| self._action_size = enviroment.action_space.n | |
| self._optimizer = optimizer | |
| self.expirience_replay = deque(maxlen=2000) | |
| # Initialize discount and exploration rate | |
| self.gamma = 0.6 | |
| self.epsilon = 0.1 | |
| # Build networks | |
| self.q_network = self._build_compile_model() | |
| self.target_network = self._build_compile_model() | |
| self.alighn_target_model() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment