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

File extract_demo.py

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

Source from the content-addressed store, hash-verified

1"""Extract a replayable demo from a Go-Explore Phase 1 run, for robustification.
2
3The backward algorithm (3-robustify.py) needs, for the best trajectory the
4archive found:

Callers

nothing calls this directly

Calls 1

mainFunction · 0.70

Tested by

no test coverage detected