def main():
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument('--env',
help='environment ID',
default='BreakoutNoFrameskip-v4')
parser.add_argument('--seed', help='RNG seed', type=int, default=0)
parser.add_argument('--prioritized', type=int, default=1)
parser.add_argument('--dueling', type=int, default=1)
parser.add_argument('--num-timesteps', type=int, default=int(10e6))
args = parser.parse_args()
logger.configure()
set_global_seeds(args.seed)
env = make_atari(args.env)
env = bench.Monitor(env, logger.get_dir())
env = HBS.wrap_atari_dqn(env)
model = HBS.models.cnn_to_mlp(
convs=[(32, 8, 4), (64, 4, 2), (64, 3, 1)],
hiddens=[256],
dueling=bool(args.dueling),
)
act = HBS.learn(env,
q_func=model,
lr=1e-4,
max_timesteps=args.num_timesteps,
buffer_size=10000,
exploration_fraction=0.1,
exploration_final_eps=0.01,
train_freq=4,
learning_starts=10000,
target_network_update_freq=1000,
gamma=0.99,
prioritized_replay=bool(args.prioritized))
# act.save("pong_model.pkl") XXX
env.close()
def main():
env = gym.make("Pendulum-v0")
'''
we assume that we have actor_list, which is a list of pre-trained policies
to be used as subpolicies
'''
exp_name = 'boundary'
actor_list = ["half_down", "half_up"]
sub_policies = []
for actor in actor_list:
print("=== Actor: {}".format(actor))
actor = HBS.load("pendulum_model_{}.pkl".format(actor), actor)
sub_policies.append(actor)
boundary_model = HBS.models.mlp([256, 256])
boundary_act = HBS.learn(env,
q_func=boundary_model,
sub_policies=sub_policies,
lr=1e-4,
max_timesteps=400000,
buffer_size=50000,
exploration_fraction=0.1,
exploration_final_eps=0.02,
print_freq=10,
exp_name=exp_name,
callback=callback)
print("Saving model to pendulum_model.pkl")
boundary_act.save("pendulum_model_{}.pkl".format(exp_name))
def main():
env = gym.make("Pendulum-v0")
model = HBS.models.mlp([256, 256])
act = HBS.learn(env,
q_func=model,
lr=1e-4,
max_timesteps=400000,
buffer_size=50000,
exploration_fraction=0.1,
exploration_final_eps=0.02,
print_freq=10,
callback=callback)
print("Saving model to cartpole_model.pkl")
act.save("cartpole_model.pkl")
def main():
env = gym.make("MountainCar-v0")
# Enabling layer_norm here is import for parameter space noise!
model = HBS.models.mlp([64], layer_norm=True)
act = HBS.learn(env,
q_func=model,
lr=1e-3,
max_timesteps=100000,
buffer_size=50000,
exploration_fraction=0.1,
exploration_final_eps=0.1,
print_freq=10,
param_noise=True)
print("Saving model to mountaincar_model.pkl")
act.save("mountaincar_model.pkl")