where do you use "next_state" in def train(self):

[yoshina621]

you get next_state from self.get_n_step_info(self.n_step_buffer, self.gamma), but the next_state is not used. may be self.store_transition(p, obs, action, reward, next_obs, done) should be self.store_transition(p, obs, action, reward, next_state, done).

[Huixxi]

Oh, sorry, I just see this issue. I think maybe you're right, thanks a lot dude, I've corrected it to reward, next_obs, done = self.get_n_step_info(self.n_step_buffer, self.gamma). You can check it now.