How to use the stable-baselines.stable_baselines.bench.monitor.Monitor.EXT function in stable-baselines

To help you get started, we’ve selected a few stable-baselines examples, based on popular ways it is used in public projects.

Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.

github harvard-edge / quarl / stable-baselines / stable_baselines / bench / monitor.py View on Github external
"""
        A monitor wrapper for Gym environments, it is used to know the episode reward, length, time and other data.

        :param env: (gym.Env) The environment
        :param filename: (Optional[str]) the location to save a log file, can be None for no log
        :param allow_early_resets: (bool) allows the reset of the environment before it is done
        :param reset_keywords: (tuple) extra keywords for the reset call, if extra parameters are needed at reset
        :param info_keywords: (tuple) extra information to log, from the information return of environment.step
        """
        super(Monitor, self).__init__(env=env)
        self.t_start = time.time()
        if filename is None:
            self.file_handler = None
            self.logger = None
        else:
            if not filename.endswith(Monitor.EXT):
                if os.path.isdir(filename):
                    filename = os.path.join(filename, Monitor.EXT)
                else:
                    filename = filename + "." + Monitor.EXT
            self.file_handler = open(filename, "wt")
            self.file_handler.write('#%s\n' % json.dumps({"t_start": self.t_start, 'env_id': env.spec and env.spec.id}))
            self.logger = csv.DictWriter(self.file_handler,
                                         fieldnames=('r', 'l', 't') + reset_keywords + info_keywords)
            self.logger.writeheader()
            self.file_handler.flush()

        self.reset_keywords = reset_keywords
        self.info_keywords = info_keywords
        self.allow_early_resets = allow_early_resets
        self.rewards = None
        self.needs_reset = True
github harvard-edge / quarl / stable-baselines / stable_baselines / bench / monitor.py View on Github external
:param env: (gym.Env) The environment
        :param filename: (Optional[str]) the location to save a log file, can be None for no log
        :param allow_early_resets: (bool) allows the reset of the environment before it is done
        :param reset_keywords: (tuple) extra keywords for the reset call, if extra parameters are needed at reset
        :param info_keywords: (tuple) extra information to log, from the information return of environment.step
        """
        super(Monitor, self).__init__(env=env)
        self.t_start = time.time()
        if filename is None:
            self.file_handler = None
            self.logger = None
        else:
            if not filename.endswith(Monitor.EXT):
                if os.path.isdir(filename):
                    filename = os.path.join(filename, Monitor.EXT)
                else:
                    filename = filename + "." + Monitor.EXT
            self.file_handler = open(filename, "wt")
            self.file_handler.write('#%s\n' % json.dumps({"t_start": self.t_start, 'env_id': env.spec and env.spec.id}))
            self.logger = csv.DictWriter(self.file_handler,
                                         fieldnames=('r', 'l', 't') + reset_keywords + info_keywords)
            self.logger.writeheader()
            self.file_handler.flush()

        self.reset_keywords = reset_keywords
        self.info_keywords = info_keywords
        self.allow_early_resets = allow_early_resets
        self.rewards = None
        self.needs_reset = True
        self.episode_rewards = []
        self.episode_lengths = []

stable-baselines

A fork of OpenAI Baselines, implementations of reinforcement learning algorithms.

MIT
Latest version published 4 years ago

Package Health Score

60 / 100
Full package analysis

Similar packages