Function get_scaler

tf2.0/mlp_trader.py:58–72

(env)

def get_scaler(env):
  # return scikit-learn scaler object to scale the states
  # Note: you could also populate the replay buffer here

  states = []
  for _ in range(env.n_step):
    action = np.random.choice(env.action_space)
    state, reward, done, info = env.step(action)
    states.append(state)
    if done:
      break

  scaler = StandardScaler()
  scaler.fit(states)
  return scaler