MCPcopy Index your code
hub / github.com/lazyprogrammer/machine_learning_examples / __init__

Method __init__

tf2.0/rl_trader.py:260–268  ·  view source on GitHub ↗
(self, state_size, action_size)

Source from the content-addressed store, hash-verified

258
259class DQNAgent(object):
260 def __init__(self, state_size, action_size):
261 self.state_size = state_size
262 self.action_size = action_size
263 self.memory = ReplayBuffer(state_size, action_size, size=500)
264 self.gamma = 0.95 # discount rate
265 self.epsilon = 1.0 # exploration rate
266 self.epsilon_min = 0.01
267 self.epsilon_decay = 0.995
268 self.model = mlp(state_size, action_size)
269
270
271 def update_replay_memory(self, state, action, reward, next_state, done):

Callers

nothing calls this directly

Calls 2

ReplayBufferClass · 0.70
mlpFunction · 0.70

Tested by

no test coverage detected