action='store_true',
help='Use simple MLP on CartPole')
parser.add_argument('--variable-ep-len',
action='store_true',
help="Change max episode length during training")
parser.add_argument('--silent',
action='store_true',
help='Silence print statements during training')
parser.add_argument('--test',
action='store_true',
help='Just render the env, no training')
if __name__ == '__main__':
args = parser.parse_args()
assert args.n % 2 == 0
chkpt_dir = 'checkpoints/%s/' % args.env_name
if not os.path.exists(chkpt_dir):
os.makedirs(chkpt_dir)
synced_model = ES(args.small_net)
for param in synced_model.parameters():
param.requires_grad = False
if args.restore:
state_dict = torch.load(args.restore)
synced_model.load_state_dict(state_dict)
if args.test:
render_env(args, synced_model)
else:
train_loop(args, synced_model, chkpt_dir)
help='Silence print statements during training')
parser.add_argument('--test',
action='store_true',
help='Just render the env, no training')
if __name__ == '__main__':
args = parser.parse_args()
assert args.n % 2 == 0
if args.small_net and args.env_name not in [
'CartPole-v0', 'CartPole-v1', 'MountainCar-v0'
]:
args.env_name = 'CartPole-v1'
print('Switching env to CartPole')
env = create_atari_env(args.env_name)
chkpt_dir = 'checkpoints/%s/' % args.env_name
if not os.path.exists(chkpt_dir):
os.makedirs(chkpt_dir)
synced_model = ES(env.observation_space.shape[0], env.action_space,
args.small_net)
for param in synced_model.parameters():
param.requires_grad = False
if args.restore:
state_dict = torch.load(args.restore)
synced_model.load_state_dict(state_dict)
if args.test:
render_env(args, synced_model, env)
else:
train_loop(args, synced_model, env, chkpt_dir)
help='Silence print statements during training')
parser.add_argument('--test',
action='store_true',
help='Just render the env, no training')
parser.add_argument('--max-gradient-updates',
type=int,
default=100000,
metavar='MGU',
help='maximum number of updates')
if __name__ == '__main__':
args = parser.parse_args()
assert args.n % 2 == 0
chkpt_dir = 'checkpoints/'
if not os.path.exists(chkpt_dir):
os.makedirs(chkpt_dir)
env = TicTacToeEnv()
synced_model = ES(env.observation_space, env.action_space)
for param in synced_model.parameters():
param.requires_grad = False
if args.restore:
state_dict = torch.load(args.restore)
synced_model.load_state_dict(state_dict)
if args.test:
render_env(synced_model)
else:
train_loop(args, synced_model, chkpt_dir)