import datetime import json import logging import os import sys import time import argparse from desktop_env.envs.desktop_env import DesktopEnv # Logger Configs {{{ # logger = logging.getLogger() logger.setLevel(logging.DEBUG) datetime_str: str = datetime.datetime.now().strftime("%Y%m%d@%H%M%S") file_handler = logging.FileHandler(os.path.join("logs", "normal-{:}.log".format(datetime_str)), encoding="utf-8") debug_handler = logging.FileHandler(os.path.join("logs", "debug-{:}.log".format(datetime_str)), encoding="utf-8") stdout_handler = logging.StreamHandler(sys.stdout) sdebug_handler = logging.FileHandler(os.path.join("logs", "sdebug-{:}.log".format(datetime_str)), encoding="utf-8") file_handler.setLevel(logging.INFO) debug_handler.setLevel(logging.DEBUG) stdout_handler.setLevel(logging.INFO) sdebug_handler.setLevel(logging.DEBUG) formatter = logging.Formatter( fmt="\x1b[1;33m[%(asctime)s \x1b[31m%(levelname)s \x1b[32m%(module)s/%(lineno)d-%(processName)s\x1b[1;33m] \x1b[0m%(message)s") file_handler.setFormatter(formatter) debug_handler.setFormatter(formatter) stdout_handler.setFormatter(formatter) sdebug_handler.setFormatter(formatter) stdout_handler.addFilter(logging.Filter("desktopenv")) sdebug_handler.addFilter(logging.Filter("desktopenv")) logger.addHandler(file_handler) logger.addHandler(debug_handler) logger.addHandler(stdout_handler) logger.addHandler(sdebug_handler) # }}} Logger Configs # logger = logging.getLogger("desktopenv.main") def human_agent(): """ Runs the Gym environment with human input. """ parser = argparse.ArgumentParser() parser.add_argument('-p', '--path', type=str, required=True, help="Path to the virtual machine .vmx file.") parser.add_argument('-s', '--snapshot', type=str, help="Name of the snapshot to restore.") parser.add_argument('-e', '--example', type=str, help="Path to the example json file.") args = parser.parse_args(sys.argv[1:]) example_path = args.example if args.example is not None and os.path.exists(args.example) else \ 'evaluation_examples/examples/libreoffice_writer/6a33f9b9-0a56-4844-9c3f-96ec3ffb3ba2.json' with open(example_path, "r") as f: example = json.load(f) # change to your customized snapshot if args.snapshot is not None: example["snapshot"] = args.snapshot assert os.path.exists(args.path), "The specified path to the .vmx file does not exist." env = DesktopEnv( path_to_vm=args.path, action_space="computer_13", task_config=example ) # reset the environment to certain snapshot observation = env.reset() logger.info('\x1b[32m[TASK INSTRUCTION]: \x1b[32;3m%s\x1b[0m', example["instruction"]) done = False trajectory = [ # { # "action_type": "MOVE_TO", # "parameters": { # "x": 754, # "y": 1057 # } # }, # {"action_type": "CLICK", "parameters": {"button": "right", "num_clicks": 1}} ] for i in range(len(trajectory)): # action = get_human_action() # action = { # "action_type": 0, # "click_type": 3, # } logger.info(trajectory[i]) observation, reward, done, info = env.step(trajectory[i]) observation.pop("accessibility_tree") logger.info("Observation: %s", observation) logger.info("Reward: %.2f", reward) logger.info("Info: %s", info) logger.info("================================\n") if done: logger.info("The episode is done.") break input("Press Enter to start human operation...") human_start_time = time.time() input("Press Enter to finish human operation.") print("Time elapsed of human operation: %.2f" % (time.time() - human_start_time)) result = env.evaluate() logger.info("Result: %.2f", result) # env.close() logger.info("Environment closed.") if __name__ == "__main__": human_agent()