209         reward      = self.decode_reward(reward_symbols)
213         return (observation, reward)
227     def encode_percept(self, observation, reward):  argument
237         symbol_list  = util.encode(reward, self.environment.reward_bits())
287         observation, reward = self.decode_percept(percept_symbols)
290         self.total_reward += reward
294         return (observation, reward)
395     def model_update_percept(self, observation, reward):  argument
409         percept_symbols = self.encode_percept(observation, reward)
421         self.total_reward += reward
425     def percept_probability(self, observation, reward):  argument
440         percept_symbols = self.encode_percept(observation, reward)
467             observation, reward = self.generate_percept_and_update()
470             total_reward += reward