| 247 | |
| 248 | |
| 249 | class Mario: |
| 250 | def __init__(): |
| 251 | pass |
| 252 | |
| 253 | def act(self, state): |
| 254 | """Given a state, choose an epsilon-greedy action""" |
| 255 | pass |
| 256 | |
| 257 | def cache(self, experience): |
| 258 | """Add the experience to memory""" |
| 259 | pass |
| 260 | |
| 261 | def recall(self): |
| 262 | """Sample experiences from memory""" |
| 263 | pass |
| 264 | |
| 265 | def learn(self): |
| 266 | """Update online action value (Q) function with a batch of experiences""" |
| 267 | pass |
| 268 | |
| 269 | |
| 270 | ###################################################################### |