ucaiado / rl_trading Goto Github PK

import gym
env = gym.make('YieldCurve')
for i_episode in range(20):
   # here I am not so sure. 
    observation = env.reset()
    for t in range(100):
        # it is equivalent to do a random action
        action = env.action_space.sample()
       # the environment step would answer with all info needed
       # now, the environment answer with the msgs generated by the
       # interaction between env and agent
        observation, reward, done, info = env.step(action)
       # the flag done could be used by different reasons
        if done:
            print("Episode finished after {} timesteps".format(t+1))
            break

if self.primary_agent == agent:
    if carry_pos and f_pos != 0:
        # set up d_pos variable properly
        if s_instr not in d_pos:
            d_pos[s_instr] = {}
        d_pos[s_instr]['Q'] = f_pos
        d_pos[s_instr]['P'] = f_price_adj

if self.primary_agent:  # include this line
    if self.primary_agent == agent:
        if carry_pos and f_pos != 0:
            # set up d_pos variable properly
            if s_instr not in d_pos:
                d_pos[s_instr] = {}
            d_pos[s_instr]['Q'] = f_pos
            d_pos[s_instr]['P'] = f_price_adj

            # log metrics
            f_pnl = float('{:0.2f}'.format(d_info['pnl']))
            na_pnl = filterout_outliers(d_info['pnl_hist'], d_info['time'])

            # calculate the MDD
            f_max = 0.
            l_aux = []
            for f_pnl in na_pnl:
                if f_pnl > f_max:
                    f_max = f_pnl
                    l_aux.append(f_max-f_pnl)

    def _basic(self, e, f_aux, s_valfunc=None, i_version=None):
        '''
        '''
        s_fdate = e.order_matching.s_file.split('_')[0].split('/')[-1]
        e.set_reward_function('pnl')
        s_hedging_on = self._get_from_argv('s_hedging_on')

        s1 = e.s_main_intrument[-3:]
        s2 = s_hedging_on[-3:]
        e.set_log_file('basic_{}{}_{}'.format(s1, s2, s_fdate))

        b_hedging = self._get_from_argv('b_hedging')
        b_hedging = True
        # check if there are initial positions
        d_initial_pos = self._get_from_argv('d_initial_pos')
        b_keep_pos = self._get_from_argv('b_keep_pos')
        if not d_initial_pos:
            d_initial_pos = {}
        if not s_hedging_on:
            s_hedging_on = 'DI1F19'
        a = e.create_agent(BasicAgent,
                           f_min_time=f_aux,
                           d_initial_pos=d_initial_pos,
                           f_ttoupdate=30.)

        return a

    def set_experiments_options(self):
        '''
        '''
        d_experiments = {'_basic': self._basic,
                         '_qlearning': self._qlearning,
                         '_domino_q': self._domino_q,
                         '_random': self._random,
                         '_domino_rand': self._domino_rand}
        return d_experiments