MCPcopy Create free account
hub / github.com/OptMLGroup/DeepBeerInventory-RL / train

Method train

SRDQN.py:366–400  ·  view source on GitHub ↗
(self,nextObservation,action,reward,terminal,playType)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers 1

playGameMethod · 0.80

Calls 2

trainQNetworkMethod · 0.95
epsilonReduceMethod · 0.95

Tested by

no test coverage detected