def encode_percept(self, observation, reward): """ Returns the given percept (an observation, reward part) as a list of symbols. - `observation`: the observation part of the percept to encode. - `reward`: the reward part of the percept to encode. """ # Add first the encoded reward, then the encoded observation to the list of output symbols. symbol_list = util.encode(reward, self.environment.reward_bits()) symbol_list += util.encode(observation, self.environment.observation_bits()) # Return the generated list. return symbol_list
def encode_percept(self, observation, reward): """ Returns the given percept (an observation, reward part) as a list of symbols. - `observation`: the observation part of the percept to encode. - `reward`: the reward part of the percept to encode. (Called `encode_percept` in the C++ version.) """ # Add first the encoded reward, then the encoded observation to the list of output symbols. symbol_list = util.encode(reward, self.environment.reward_bits()) symbol_list += util.encode(observation, self.environment.observation_bits()) # Return the generated list. return symbol_list
def encode_action(self, action): """ Returns the given action encoded as a list of symbols. - `action`: the action to encode. """ return util.encode(action, self.environment.action_bits())
def encode_action(self, action): """ Returns the given action encoded as a list of symbols. - `action`: the action to encode. (Called `encodeAction` in the C++ version.) """ return util.encode(action, self.environment.action_bits())