MCPcopy Create free account
hub / github.com/rlcode/reinforcement-learning / record

Method record

4-atari-hard/env_robustify.py:204–206  ·  view source on GitHub ↗
(self, starting_point, success)

Source from the content-addressed store, hash-verified

202 e.starting_point = max(self.max_starting_point - i * per, 0)
203
204 def record(self, starting_point, success):
205 # exponential-ish freshening: latest wins (atari-reset keeps last rate)
206 self.success[min(starting_point, self.n)] = float(success)
207
208 def update(self, envs):
209 """Move rule (atari-reset ResetManager.proc_infos): forward-cumsum the

Callers 1

mainFunction · 0.95

Calls

no outgoing calls

Tested by

no test coverage detected