def test_env_buy(self):
trade = Trade()
trade.new_episode()
print(trade.time)
trade.step(ACTION.BUY)
print(trade.time)
def test_buy_order(self):
trade = Trade()
trade.new_episode()
print(trade.time)
trade.step(ACTION.BUY)
print(trade.time)
print(trade.buy_order_price)
print(trade.margin)
def test_sell_order(self):
trade = Trade()
trade.new_episode()
print(trade.time)
trade.step(ACTION.SELL)
print(trade.time)
print(trade.sell_order_price)
print(trade.margin)
def test_env_sell_buy(self):
trade = Trade()
trade.new_episode()
print(trade.time)
trade.step(ACTION.SELL_NOW)
print(trade.time)
print(trade.sell_order_price)
print(trade.margin)
# close transaction
print(trade.time)
trade.step(ACTION.BUY_NOW)
print(trade.time)
print(trade.margin)
def test_env_step(self):
trade = Trade()
trade.new_episode()
trade.step(ACTION.NOP)
trade.step(ACTION.BUY)
trade.step(ACTION.BUY_NOW)
trade.step(ACTION.SELL)
trade.step(ACTION.SELL_NOW)
def one_episode(self, env: Trade):
s = env.new_episode()
while True:
action = self.policy(s)
print('action->', action, end='')
next_state, reward, done, info = env.step(action)
print('reward->', reward)
if done:
break
s = next_state
return reward
