MCPcopy Create free account
hub / github.com/rlcode/reinforcement-learning / 3-robustify.py

File 3-robustify.py

4-atari-hard/3-robustify.py:None–None  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

1"""Go-Explore robustification (backward algorithm) for Montezuma's Revenge.
2
3Salimans & Chen 2018 (arXiv:1812.03381) + Go-Explore Nature robustification.
4Distills the single deterministic demo found by Phase 1 (2-go-explore.py, score

Callers

nothing calls this directly

Calls 1

mainFunction · 0.70

Tested by

no test coverage detected