(self, state)
| 261 | |
| 262 | |
| 263 | def act(self, state): |
| 264 | if np.random.rand() <= self.epsilon: |
| 265 | return np.random.choice(self.action_size) |
| 266 | act_values = self.model.predict(state) |
| 267 | return np.argmax(act_values[0]) # returns action |
| 268 | |
| 269 | def replay(self, batch_size=32): |
| 270 | # first check if replay buffer contains enough data |
no test coverage detected