def run_experiment(configpath: str, random_seed: int, noconfig: bool):
"""
Runs one experiment and saves results and plots
:param configpath: path to configfile
:param noconfig: whether to override config
:return: (train_csv_path, eval_csv_path)
"""
if configpath is not None and not noconfig:
if not os.path.exists(args.configpath):
write_default_config()
config = util.read_config(args.configpath)
else:
config = default_config()
time_str = str(time.time())
util.create_artefact_dirs(config.output_dir, random_seed)
logger = util.setup_logger("maximal_attack_vs_reinforce-v9",
config.output_dir + "/results/logs/" +
str(random_seed) + "/",
time_str=time_str)
config.pg_agent_config.save_dir = default_output_dir(
) + "/results/data/" + str(random_seed) + "/"
config.pg_agent_config.video_dir = default_output_dir(
) + "/results/videos/" + str(random_seed) + "/"
config.pg_agent_config.gif_dir = default_output_dir(
) + "/results/gifs/" + str(random_seed) + "/"
config.pg_agent_config.tensorboard_dir = default_output_dir() + "/results/tensorboard/" \
+ str(random_seed) + "/"
config.logger = logger
config.pg_agent_config.logger = logger
config.pg_agent_config.random_seed = random_seed
config.random_seed = random_seed
config.pg_agent_config.to_csv(config.output_dir +
"/results/hyperparameters/" +
str(random_seed) + "/" + time_str + ".csv")
train_csv_path = ""
eval_csv_path = ""
if config.hp_tuning:
hp_tuning.hype_grid(config)
else:
train_result, eval_result = Runner.run(config)
if len(train_result.avg_episode_steps) > 0 and len(
eval_result.avg_episode_steps) > 0:
train_csv_path = config.output_dir + "/results/data/" + str(
random_seed) + "/" + time_str + "_train" + ".csv"
train_result.to_csv(train_csv_path)
eval_csv_path = config.output_dir + "/results/data/" + str(
random_seed) + "/" + time_str + "_eval" + ".csv"
eval_result.to_csv(eval_csv_path)
plot_csv(config, eval_csv_path, train_csv_path, random_seed)
return train_csv_path, eval_csv_path
def run_experiment(configpath: str, random_seed: int, noconfig: bool):
"""
Runs one experiment and saves results and plots
:param config: experiment configuration
:param noconfig: whether to override config
:return: (train_csv_path, eval_csv_path)
"""
if configpath is not None and not noconfig:
if not os.path.exists(configpath):
write_default_config()
config = util.read_config(configpath)
else:
config = default_config()
time_str = str(time.time())
util.create_artefact_dirs(config.output_dir, random_seed)
logger = util.setup_logger("tabular_q_learning_vs_tabular_q_learning-v0",
config.output_dir + "/results/logs/" +
str(random_seed) + "/",
time_str=time_str)
config.q_agent_config.save_dir = default_output_dir(
) + "/results/data/" + str(random_seed) + "/"
config.q_agent_config.video_dir = default_output_dir(
) + "/results/videos/" + str(random_seed) + "/"
config.q_agent_config.gif_dir = default_output_dir(
) + "/results/gifs/" + str(random_seed) + "/"
config.logger = logger
config.q_agent_config.logger = logger
config.q_agent_config.random_seed = random_seed
config.random_seed = random_seed
config.q_agent_config.to_csv(config.output_dir +
"/results/hyperparameters/" +
str(random_seed) + "/" + time_str + ".csv")
train_result, eval_result = Runner.run(config)
train_csv_path = ""
eval_csv_path = ""
if len(train_result.avg_episode_steps) > 0 and len(
eval_result.avg_episode_steps) > 0:
train_csv_path = config.output_dir + "/results/data/" + str(
random_seed) + "/" + time_str + "_train" + ".csv"
train_result.to_csv(train_csv_path)
eval_csv_path = config.output_dir + "/results/data/" + str(
random_seed) + "/" + time_str + "_eval" + ".csv"
eval_result.to_csv(eval_csv_path)
plot_csv(config, eval_csv_path, train_csv_path, random_seed)
return train_csv_path, eval_csv_path
def setup_train(config: ClientConfig, random_seed):
time_str = str(time.time())
util.create_artefact_dirs(config.output_dir, random_seed)
logger = util.setup_logger("tabular_q_vs_random_defense-v3",
config.output_dir + "/results/logs/" +
str(random_seed) + "/",
time_str=time_str)
config.q_agent_config.save_dir = default_output_dir(
) + "/results/data/" + str(random_seed) + "/"
config.q_agent_config.video_dir = default_output_dir(
) + "/results/videos/" + str(random_seed) + "/"
config.q_agent_config.gif_dir = default_output_dir(
) + "/results/gifs/" + str(random_seed) + "/"
# config.q_agent_config.dqn_config.tensorboard_dir = default_output_dir() + "/results/tensorboard/" \
# + str(random_seed) + "/"
config.logger = logger
config.q_agent_config.logger = logger
config.q_agent_config.random_seed = random_seed
config.random_seed = random_seed
config.q_agent_config.to_csv(config.output_dir +
"/results/hyperparameters/" +
str(random_seed) + "/" + time_str + ".csv")
return time_str
attacker_cumulative_reward=df["attacker_cumulative_reward"],
defender_cumulative_reward=df["defender_cumulative_reward"],
log_frequency=config.simulation_config.log_frequency,
output_dir=config.output_dir, eval=False, sim=True)
# Program entrypoint
if __name__ == '__main__':
args = util.parse_args(default_config_path())
if args.configpath is not None:
if not os.path.exists(args.configpath):
write_default_config()
config = util.read_config(args.configpath)
else:
config = default_config()
time_str = str(time.time())
util.create_artefact_dirs(config.output_dir)
logger = util.setup_logger("idsgame-v0-random_vs_defend_minimal", config.output_dir + "/logs/",
time_str=time_str)
config.logger = logger
config.simulation_config.logger = logger
config.simulation_config.to_csv(config.output_dir + "/hyperparameters/" + time_str + ".csv")
result = Runner.run(config)
if len(result.avg_episode_steps) > 0:
csv_path = config.output_dir + "/data/" + time_str + "_simulation" + ".csv"
result.to_csv(csv_path)
plot_csv(config, csv_path)
"""
return os.path.dirname(os.path.realpath(sys.argv[0]))
def default_output_dir() -> str:
"""
:return: the default output dir
"""
script_dir = get_script_path()
return script_dir
# Program entrypoint
if __name__ == '__main__':
random_seed = 0
util.create_artefact_dirs(default_output_dir(), random_seed)
pg_agent_config = PolicyGradientAgentConfig(
gamma=1,
alpha_attacker=0.0001,
epsilon=1,
render=False,
alpha_defender=0.0001,
eval_sleep=0.9,
min_epsilon=0.01,
eval_episodes=1000,
train_log_frequency=1,
epsilon_decay=0.9999,
video=True,
eval_log_frequency=500,
video_fps=5,
video_dir=default_output_dir() + "/results/videos",