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

Class Cell

4-atari-hard/2-go-explore.py:76–89  ·  view source on GitHub ↗

Archive entry. snapshot/lives describe the state AT this cell so a worker can restore and keep exploring; traj_last points into the experience log for trajectory reconstruction.

Source from the content-addressed store, hash-verified

74
75
76class Cell:
77 """Archive entry. snapshot/lives describe the state AT this cell so a
78 worker can restore and keep exploring; traj_last points into the
79 experience log for trajectory reconstruction."""
80 __slots__ = ("snapshot", "score", "traj_len", "traj_last",
81 "seen", "chosen", "chosen_since_new", "lives")
82
83 def __init__(self, snapshot, score, traj_len, traj_last, lives):
84 self.snapshot = snapshot
85 self.score = score
86 self.traj_len = traj_len
87 self.traj_last = traj_last
88 self.lives = lives
89 self.seen = self.chosen = self.chosen_since_new = 0
90
91
92class ExperienceLog:

Callers 3

seed_rootMethod · 0.85
load_stateMethod · 0.85

Calls

no outgoing calls

Tested by

no test coverage detected