MCPcopy Index your code
hub / github.com/pytorch/tutorials / Mario

Class Mario

intermediate_source/mario_rl_tutorial.py:249–267  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

247
248
249class 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######################################################################

Callers 1

Calls

no outgoing calls

Tested by

no test coverage detected