def _gather_infos()

in textworld/envs/tw.py [0:0]


    def _gather_infos(self):
        self.state["game"] = self._game
        self.state["command_templates"] = self._game.command_templates
        self.state["verbs"] = self._game.verbs
        self.state["entities"] = self._game.entity_names
        self.state["objective"] = self._game.objective
        self.state["max_score"] = self._game.max_score

        for k, v in self._game.metadata.items():
            self.state["extra.{}".format(k)] = v

        self.state["_game_progression"] = self._game_progression
        self.state["_facts"] = list(self._game_progression.state.facts)

        self.state["won"] = self._game_progression.completed
        self.state["lost"] = self._game_progression.failed

        self.state["_winning_policy"] = self._current_winning_policy
        if self.infos.policy_commands:
            self.state["policy_commands"] = []
            if self._game_progression.winning_policy is not None:
                self.state["policy_commands"] = self._inform7.gen_commands_from_actions(self._current_winning_policy)

        if self.infos.intermediate_reward:
            self.state["intermediate_reward"] = 0
            if self.state["won"]:
                # The last action led to winning the game.
                self.state["intermediate_reward"] = 1

            elif self.state["lost"]:
                # The last action led to losing the game.
                self.state["intermediate_reward"] = -1

            elif self._previous_winning_policy is None:
                self.state["intermediate_reward"] = 0

            else:
                diff = len(self._previous_winning_policy) - len(self._current_winning_policy)
                self.state["intermediate_reward"] = int(diff > 0) - int(diff < 0)  # Sign function.

        if self.infos.facts:
            self.state["facts"] = list(map(self._inform7.get_human_readable_fact, self.state["_facts"]))

        self.state["last_action"] = None
        self.state["_last_action"] = self._last_action
        if self.infos.last_action and self._last_action is not None:
            self.state["last_action"] = self._inform7.get_human_readable_action(self._last_action)

        self.state["_valid_actions"] = self._game_progression.valid_actions
        self.state["_valid_commands"] = self._inform7.gen_commands_from_actions(self._game_progression.valid_actions)
        # To guarantee the order from one execution to another, we sort the commands.
        # Remove any potential duplicate commands (they would lead to the same result anyway).
        self.state["admissible_commands"] = sorted(set(self.state["_valid_commands"]))

        if self.infos.moves:
            self.state["moves"] = self._moves