(self, state)
| 302 | |
| 303 | |
| 304 | def act(self, state): |
| 305 | if np.random.rand() <= self.epsilon: |
| 306 | return np.random.choice(self.action_size) |
| 307 | act_values = predict(self.model, state) |
| 308 | return np.argmax(act_values[0]) # returns action |
| 309 | |
| 310 | |
| 311 | def replay(self, batch_size=32): |
no test coverage detected