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

Method _frame

4-atari-hard/env_robustify.py:95–98  ·  view source on GitHub ↗
(self)

Source from the content-addressed store, hash-verified

93 # keeps us light and matches the rest of this repo). 4-stack handled in
94 # the trainer. Returns uint8 (105, 80). ---
95 def _frame(self):
96 import cv2
97 g = self.ale.getScreenGrayscale()
98 return cv2.resize(g, (80, 105), interpolation=cv2.INTER_AREA)
99
100 def _restore_to(self, nr):
101 """Restore the latest checkpoint at or before nr, replay demo actions

Callers 1

_step_rawMethod · 0.95

Calls

no outgoing calls

Tested by

no test coverage detected