def parse_args():
"""
parse the arguments for DDPG training
:return: (dict) the arguments
"""
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument('--config',
type=str,
default='cfg/train_no_teachers.yaml')
parser.add_argument('--log-base-dir', type=str, default=None)
parser.add_argument('--log-dir', type=str, default=None)
parser.add_argument('--experiment-name', type=str, default=None)
parser.add_argument('--load-path', type=str, default=None)
parser.add_argument('--learner-type',
type=str,
choices=['DDPG', 'Q'],
default=None)
# Can optionally overwrite some params from config
parser.add_argument('--env-id', type=str, default=None)
parser.add_argument('--teacher_behavior_policy', type=str, default=None)
parser.add_argument('--seed', help='RNG seed', type=int, default=None)
parser.add_argument('--batch-size', type=int,
default=None) # per MPI worker
parser.add_argument('--reward-scale', type=float, default=None)
parser.add_argument('--noise-type', type=str, default=None)
parser.add_argument('--feature-extraction', type=str, default=None)
parser.add_argument('--nb-train-steps', type=int,
default=None) # per epoch cycle and MPI worker
parser.add_argument('--nb-rollout-steps', type=int,
default=None) # per epoch cycle and MPI worker
parser.add_argument('--num-timesteps', type=int, default=None)
parser.add_argument('--nb-eval-steps', type=int,
default=None) # per epoch cycle and MPI worker
parser.add_argument('--log-interval', type=int,
default=None) # per epoch cycle and MPI worker
#parser.add_argument('--demo-path', type=str, default='')
parser.add_argument(
"--load-from",
type=str,
help="load the saved model and optimizer at the beginning")
boolean_flag(parser, 'do_eval', default=None)
boolean_flag(parser, 'render-eval', default=None)
boolean_flag(parser, 'render', default=None)
boolean_flag(parser, 'save_exps', default=None)
args = parser.parse_args()
dict_args = vars(args)
return dict_args
def argsparser():
"""
make a argument parser for evaluation of gail
:return: (ArgumentParser)
"""
parser = argparse.ArgumentParser('Do evaluation')
parser.add_argument('--seed', type=int, default=0)
parser.add_argument('--policy_hidden_size', type=int, default=100)
parser.add_argument('--env',
type=str,
choices=[
'Hopper', 'Walker2d', 'HalfCheetah', 'Humanoid',
'HumanoidStandup'
])
boolean_flag(parser,
'stochastic_policy',
default=False,
help_msg='use stochastic/deterministic policy to evaluate')
return parser.parse_args()
def argsparser():
"""
make a behavior cloning argument parser
:return: (ArgumentParser)
"""
parser = argparse.ArgumentParser(
"Tensorflow Implementation of Behavior Cloning")
parser.add_argument('--env_id', help='environment ID', default='Hopper-v1')
parser.add_argument('--seed', help='RNG seed', type=int, default=0)
parser.add_argument('--expert_path',
type=str,
default='data/deterministic.trpo.Hopper.0.00.npz')
parser.add_argument('--checkpoint_dir',
help='the directory to save model',
default='checkpoint')
parser.add_argument('--log_dir',
help='the directory to save log file',
default='log')
# Mujoco Dataset Configuration
parser.add_argument('--traj_limitation', type=int, default=-1)
# Network Configuration (Using MLP Policy)
parser.add_argument('--policy_hidden_size', type=int, default=100)
# for evaluatation
boolean_flag(parser,
'stochastic_policy',
default=False,
help_msg='use stochastic/deterministic policy to evaluate')
boolean_flag(parser,
'save_sample',
default=False,
help_msg='save the trajectories or not')
parser.add_argument('--BC_max_iter',
help='Max iteration for training BC',
type=int,
default=1e5)
return parser.parse_args()
def parse_args():
"""
parse the arguments for DDPG training
:return: (dict) the arguments
"""
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument('--env_type', type=str, default="mujoco")
parser.add_argument('--env-id', type=str, default='Ant-v2')
parser.add_argument('--agent', type=str, default='TD3')
# boolean_flag(parser, 'render-eval', default=False)
boolean_flag(parser, 'layer-norm', default=False)
boolean_flag(parser, 'evaluation', default=True)
parser.add_argument('--seed',
help='RNG seed',
type=int,
default=int(time.time()))
parser.add_argument('--comment',
help='to show name',
type=str,
default="show_name_in_htop")
parser.add_argument('--gamma', type=float, default=0.99)
parser.add_argument('--num-timesteps', type=int, default=int(1e6) +
10) # plus 10 to make one more evaluation
parser.add_argument('--max_steps', type=int,
default=1000) # truncate steps for ddq
parser.add_argument('--delay-step', type=int, default=0)
args = parser.parse_args()
dict_args = vars(args)
return dict_args
def argsparser():
"""
get an argument parser for training mujoco on gail
:return: (ArgumentParser)
"""
parser = argparse.ArgumentParser("Tensorflow Implementation of GAIL")
parser.add_argument('--env_id', help='environment ID', default='Hopper-v2')
parser.add_argument('--seed', help='RNG seed', type=int, default=0)
parser.add_argument('--expert_path', type=str, default='data/deterministic.trpo.Hopper.0.00.npz')
parser.add_argument('--checkpoint_dir', help='the directory to save model', default='checkpoint')
parser.add_argument('--log_dir', help='the directory to save log file', default='log')
parser.add_argument('--load_model_path', help='if provided, load the model', type=str, default=None)
# Task
parser.add_argument('--task', type=str, choices=['train', 'evaluate', 'sample'], default='train')
# for evaluatation
boolean_flag(parser, 'stochastic_policy', default=False, help_msg='use stochastic/deterministic policy to evaluate')
boolean_flag(parser, 'save_sample', default=False, help_msg='save the trajectories or not')
# Mujoco Dataset Configuration
parser.add_argument('--traj_limitation', type=int, default=-1)
# Optimization Configuration
parser.add_argument('--g_step', help='number of steps to train policy in each epoch', type=int, default=3)
parser.add_argument('--d_step', help='number of steps to train discriminator in each epoch', type=int, default=1)
# Network Configuration (Using MLP Policy)
parser.add_argument('--policy_hidden_size', type=int, default=100)
parser.add_argument('--adversary_hidden_size', type=int, default=100)
# Algorithms Configuration
# ----------------------------------GAIL 은 현재 trpo만 가능-----------------------------------------
parser.add_argument('--algo', type=str, default='trpo')
# ------------------------------------------------------------------------------------------------
parser.add_argument('--max_kl', type=float, default=0.01)
parser.add_argument('--policy_entcoeff', help='entropy coefficiency of policy', type=float, default=0)
parser.add_argument('--adversary_entcoeff', help='entropy coefficiency of discriminator', type=float, default=1e-3)
# Traing Configuration
parser.add_argument('--save_per_iter', help='save model every xx iterations', type=int, default=100)
parser.add_argument('--num_timesteps', help='number of timesteps per episode', type=int, default=5e6)
# Behavior Cloning
boolean_flag(parser, 'pretrained', default=False, help_msg='Use BC to pretrain')
parser.add_argument('--bc_max_iter', help='Max iteration for training BC', type=int, default=1e4)
return parser.parse_args()
def parse_args():
"""
parse the arguments for DDPG training
:return: (dict) the arguments
"""
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument('--env-id', type=str, default='HalfCheetah-v1')
boolean_flag(parser, 'render-eval', default=False)
boolean_flag(parser, 'layer-norm', default=True)
boolean_flag(parser, 'render', default=False)
boolean_flag(parser, 'normalize-returns', default=False)
boolean_flag(parser, 'normalize-observations', default=True)
parser.add_argument('--seed', help='RNG seed', type=int, default=0)
parser.add_argument('--critic-l2-reg', type=float, default=1e-2)
parser.add_argument('--batch-size', type=int, default=64) # per MPI worker
parser.add_argument('--actor-lr', type=float, default=1e-4)
parser.add_argument('--critic-lr', type=float, default=1e-3)
boolean_flag(parser, 'enable-popart', default=False)
parser.add_argument('--gamma', type=float, default=0.99)
parser.add_argument('--reward-scale', type=float, default=1.)
parser.add_argument('--clip-norm', type=float, default=None)
parser.add_argument('--nb-train-steps', type=int,
default=50) # per epoch cycle and MPI worker
parser.add_argument('--nb-eval-steps', type=int,
default=100) # per epoch cycle and MPI worker
parser.add_argument('--nb-rollout-steps', type=int,
default=100) # per epoch cycle and MPI worker
# choices are adaptive-param_xx, ou_xx, normal_xx, none
parser.add_argument('--noise-type', type=str, default='adaptive-param_0.2')
boolean_flag(parser, 'evaluation', default=False)
args = parser.parse_args()
dict_args = vars(args)
return dict_args