def parse_args():
parser = argparse.ArgumentParser("Run an already learned DQN model.")
# Environment
parser.add_argument("--env", type=str, required=True,
help="name of the game")
parser.add_argument("--model-dir", type=str, default=None,
help="load model from this directory. ")
parser.add_argument("--video", type=str, default=None,
help="Path to mp4 file where the \
video of first episode will be recorded.")
boolean_flag(parser, "stochastic", default=True,
help="whether or not to use stochastic \
actions according to models eps value")
boolean_flag(parser, "dueling", default=False,
help="whether or not to use dueling model")
# V: Attack Arguments#
parser.add_argument("--model-dir2", type=str, default=None,
help="load adversarial model from \
this directory (blackbox attacks). ")
parser.add_argument("--attack", type=str, default=None,
help="Method to attack the model.")
boolean_flag(parser, "noisy", default=False,
help="whether or not to NoisyNetwork")
boolean_flag(parser, "noisy2", default=False,
help="whether or not to NoisyNetwork")
boolean_flag(parser, "blackbox", default=False,
help="whether or not to NoisyNetwork")
return parser.parse_args()
def parse_args():
parser = argparse.ArgumentParser("DQN experiments for Atari games")
# Environment
parser.add_argument("--env", type=str, default="Pong", help="name of the game")
parser.add_argument("--seed", type=int, default=42, help="which seed to use")
# Core DQN parameters
parser.add_argument("--replay-buffer-size", type=int, default=int(1e6), help="replay buffer size")
parser.add_argument("--lr", type=float, default=1e-4, help="learning rate for Adam optimizer")
parser.add_argument("--num-steps", type=int, default=int(2e8), help="total number of steps to run the environment for")
parser.add_argument("--batch-size", type=int, default=32, help="number of transitions to optimize at the same time")
parser.add_argument("--learning-freq", type=int, default=4, help="number of iterations between every optimization step")
parser.add_argument("--target-update-freq", type=int, default=40000, help="number of iterations between every target network update")
# Bells and whistles
boolean_flag(parser, "noisy", default=False, help="whether or not to NoisyNetwork")
boolean_flag(parser, "double-q", default=True, help="whether or not to use double q learning")
boolean_flag(parser, "dueling", default=False, help="whether or not to use dueling model")
boolean_flag(parser, "prioritized", default=False, help="whether or not to use prioritized replay buffer")
parser.add_argument("--prioritized-alpha", type=float, default=0.6, help="alpha parameter for prioritized replay buffer")
parser.add_argument("--prioritized-beta0", type=float, default=0.4, help="initial value of beta parameters for prioritized replay")
parser.add_argument("--prioritized-eps", type=float, default=1e-6, help="eps parameter for prioritized replay buffer")
# Checkpointing
parser.add_argument("--save-dir", type=str, default=None, required=True, help="directory in which training state and model should be saved.")
parser.add_argument("--save-azure-container", type=str, default=None,
help="It present data will saved/loaded from Azure. Should be in format ACCOUNT_NAME:ACCOUNT_KEY:CONTAINER")
parser.add_argument("--save-freq", type=int, default=1e6, help="save model once every time this many iterations are completed")
boolean_flag(parser, "load-on-start", default=True, help="if true and model was previously saved then training will be resumed")
#V: Attack Arguments #
parser.add_argument("--attack", type=str, default=None, help="Method to attack the model.")
parser.add_argument("--attack-init", type=int, default=0, help="Iteration no. to begin attacks")
parser.add_argument("--attack-prob", type=float, default=0.0, help="Probability of attack at each step, float in range 0 - 1.0" )
return parser.parse_args()
def parse_args():
parser = argparse.ArgumentParser("DQN experiments for Atari games")
# Environment
parser.add_argument("--env", type=str, default="Pong",
help="name of the game")
parser.add_argument("--seed", type=int, default=42,
help="which seed to use")
# Core DQN parameters
parser.add_argument("--replay-buffer-size", type=int, default=int(1e6),
help="replay buffer size")
parser.add_argument("--lr", type=float, default=1e-4,
help="learning rate for Adam optimizer")
parser.add_argument("--num-steps", type=int, default=int(2e8),
help="total number of steps to \
run the environment for")
parser.add_argument("--batch-size", type=int, default=32,
help="number of transitions to optimize \
at the same time")
parser.add_argument("--learning-freq", type=int, default=4,
help="number of iterations between \
every optimization step")
parser.add_argument("--target-update-freq", type=int, default=40000,
help="number of iterations between \
every target network update")
# Bells and whistles
boolean_flag(parser, "noisy", default=False,
help="whether or not to NoisyNetwork")
boolean_flag(parser, "double-q", default=True,
help="whether or not to use double q learning")
boolean_flag(parser, "dueling", default=False,
help="whether or not to use dueling model")
boolean_flag(parser, "prioritized", default=False,
help="whether or not to use prioritized replay buffer")
parser.add_argument("--prioritized-alpha", type=float, default=0.6,
help="alpha parameter for prioritized replay buffer")
parser.add_argument("--prioritized-beta0", type=float, default=0.4,
help="initial value of beta \
parameters for prioritized replay")
parser.add_argument("--prioritized-eps", type=float, default=1e-6,
help="eps parameter for prioritized replay buffer")
# Checkpointing
parser.add_argument("--save-dir", type=str, default=None, required=True,
help="directory in which \
training state and model should be saved.")
parser.add_argument("--save-azure-container", type=str, default=None,
help="It present data will saved/loaded from Azure. \
Should be in format ACCOUNT_NAME:ACCOUNT_KEY:\
CONTAINER")
parser.add_argument("--save-freq", type=int, default=1e6,
help="save model once every time this many \
iterations are completed")
boolean_flag(parser, "load-on-start", default=True,
help="if true and model was previously saved then training \
will be resumed")
# V: Attack Arguments #
parser.add_argument("--attack", type=str, default=None,
help="Method to attack the model.")
parser.add_argument("--attack-init", type=int, default=0,
help="Iteration no. to begin attacks")
parser.add_argument("--attack-prob", type=float, default=0.0,
help="Probability of attack at each step, \
float in range 0 - 1.0")
return parser.parse_args()