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

Function epsilon

3-atari/1-dqn.py:116–119  ·  view source on GitHub ↗

Linear schedule from EPSILON_START to EPSILON_END over EPSILON_DECAY_FRAMES.

(frame)

Source from the content-addressed store, hash-verified

114
115
116def epsilon(frame):
117 """Linear schedule from EPSILON_START to EPSILON_END over EPSILON_DECAY_FRAMES."""
118 frac = min(frame / EPSILON_DECAY_FRAMES, 1.0)
119 return EPSILON_START + frac * (EPSILON_END - EPSILON_START)
120
121
122if __name__ == "__main__":

Callers 1

1-dqn.pyFile · 0.85

Calls

no outgoing calls

Tested by

no test coverage detected