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

Method state

4-atari-hard/2-go-explore.py:283–289  ·  view source on GitHub ↗
(self)

Source from the content-addressed store, hash-verified

281 self.rooms.update(res["rooms"])
282
283 def state(self):
284 return {"cells": {k: {"snapshot": c.snapshot, "score": c.score,
285 "traj_len": c.traj_len, "traj_last": c.traj_last,
286 "seen": c.seen, "chosen": c.chosen,
287 "chosen_since_new": c.chosen_since_new, "lives": c.lives}
288 for k, c in self.cells.items()},
289 "rooms": sorted(self.rooms), "done_scores": self.done_scores[-200:]}
290
291 def load_state(self, st):
292 self.cells = {}

Callers 1

_state_fnFunction · 0.45

Calls

no outgoing calls

Tested by

no test coverage detected