def sample_next_state_reward(state=state) -> Tuple[PriceState, float]:
up_prob = get_logistic_func(self.alpha1)(self.level_param -
state.price)
up_move: int = binomial(1, up_prob, 1)[0]
next_state: PriceState = PriceState(price=state.price +
up_move * 2 - 1)
reward: float = self.reward_function(next_state)
return next_state, reward
def up_prob(self, state: StateMP1) -> float:
"""
return the probability that the stock price goes up
"""
return get_logistic_func(self.alpha1)(self.level_param - state.price)
def up_prob(self, state: StateMP1) -> float:
return get_logistic_func(self.alpha1)(self.level_param - state.price)