def main(args):
if args.central_train is True:
raise NotImplementedError("todo")
# Create directories
if not os.path.exists("./logs"):
os.makedirs("./logs")
if not os.path.exists("./pytorch_models"):
os.makedirs("./pytorch_models")
# Set logs
tb_writer = SummaryWriter('./logs/tb_{0}'.format(args.log_name))
log = set_log(args)
# Create env
env = make_env(args)
# Set seeds
env.seed(args.seed)
torch.manual_seed(args.seed)
np.random.seed(args.seed)
# Initialize policy
agents = [
set_policy(env, tb_writer, log, args, name="agent", i_agent=i_agent)
for i_agent in range(args.n_agent)
]
# Start train
train(agents=agents, env=env, log=log, tb_writer=tb_writer, args=args)
def main(args):
# Create dir
if not os.path.exists("./logs"):
os.makedirs("./logs")
if not os.path.exists("./pytorch_models"):
os.makedirs("./pytorch_models")
# Set logs
tb_writer = SummaryWriter('./logs/tb_{0}'.format(args.log_name))
log = set_log(args)
# Create env
env = make_env(args)
# Set seeds
env.seed(args.seed)
torch.manual_seed(args.seed)
np.random.seed(args.seed)
# Initialize policy
student_n = [
set_policy(env, log, args, name="student", i_agent=i_agent)
for i_agent in range(args.n_student)
]
# Start train
train(student_n=student_n,
env=env,
log=log,
tb_writer=tb_writer,
args=args)
if not os.path.exists("./saved_model"):
os.makedirs("./saved_model")
def main(args):
# Create directories
if not os.path.exists("./logs"):
os.makedirs("./logs")
if not os.path.exists("./pytorch_models"):
os.makedirs("./pytorch_models")
# Set logs
log = set_log(args)
tb_writer = SummaryWriter('./logs/tb_{0}'.format(args.log_name))
# Create env
env = make_env(args)
# Set seeds
random.seed(args.seed)
np.random.seed(args.seed)
torch.manual_seed(args.seed)
env.seed(args.seed)
# Initialize agents
agent1 = Agent(env, log, tb_writer, args, name="agent1", i_agent=1)
agent2 = Agent(env, log, tb_writer, args, name="agent2", i_agent=2)
# Start train
train(agent1, agent2, env, log, tb_writer, args)
def main(args):
# Create directories
if not os.path.exists("./logs"):
os.makedirs("./logs")
if not os.path.exists("./pytorch_models"):
os.makedirs("./pytorch_models")
# Set logs
tb_writer = SummaryWriter('./logs/tb_{0}'.format(args.log_name))
log = set_log(args)
# Create env
env = make_env(log, args)
# Set seeds
env.seed(args.seed)
torch.manual_seed(args.seed)
np.random.seed(args.seed)
# Initialize policy
agent = set_policy(env, tb_writer, log, args, name=args.algorithm)
if args.test:
from tester import test
test(agent=agent, env=env, log=log, tb_writer=tb_writer, args=args)
else:
from trainer import train
train(agent=agent, env=env, log=log, tb_writer=tb_writer, args=args)
def __init__(self, args):
self.args = args
self.num_workers = mp.cpu_count() - 1
if self.num_workers > args.n_traj:
self.num_workers = args.n_traj
self.queue = mp.Queue()
self.envs = SubprocVecEnv(envs=[
make_env(args.env_name, args.n_agent)
for _ in range(self.num_workers)
],
queue=self.queue,
args=args)
# Set seed to envs
self.envs.seed(0)
def main(args):
# Create dir
if not os.path.exists("./logs"):
os.makedirs("./logs")
if not os.path.exists("./pytorch_models"):
os.makedirs("./pytorch_models")
# Set logs
tb_writer = SummaryWriter('./logs/tb_{0}'.format(args.log_name))
log = set_log(args)
# Create env
env = make_env(args)
# Set seeds
env.seed(args.seed)
torch.manual_seed(args.seed)
np.random.seed(args.seed)
# Initialize policy
opponent_n = [
set_policy(env, tb_writer, log, args, name="opponent", i_agent=i_agent)
for i_agent in range(1)
]
modeler = set_policy(env, tb_writer, log, args, name="modeler", i_agent=0)
# Start training
if args.train_opponent:
train_opponent(opponent_n=opponent_n,
env=env,
log=log,
tb_writer=tb_writer,
args=args)
else:
# Load trained opponent model
for opponent in opponent_n:
opponent.load_model(filename="opponent0_500",
directory="./pytorch_models")
train_modeler(modeler=modeler,
opponent_n=opponent_n,
env=env,
log=log,
tb_writer=tb_writer,
args=args)
def main(args):
# Create directories
if not os.path.exists("./logs"):
os.makedirs("./logs")
if not os.path.exists("./pytorch_models"):
os.makedirs("./pytorch_models")
# Set logs
tb_writer = SummaryWriter('./logs/tb_{0}'.format(args.log_name))
log = set_log(args)
# Create env
env = make_env(args)
# Set seeds
env.seed(args.seed)
torch.manual_seed(args.seed)
np.random.seed(args.seed)
# Initialize policy
# Note that only one teacher is considered in the one box push domain
# to transfer knowledge from agent $i$ to agent $k$ (Section 6.1)
workers = [
set_policy(env, tb_writer, log, args, name="worker", i_agent=i_agent)
for i_agent in range(args.n_worker)]
managers = [
set_policy(env, tb_writer, log, args, name="manager", i_agent=i_agent)
for i_agent in range(args.n_manager)]
temp_managers = [
set_policy(env, tb_writer, log, args, name="temp_manager", i_agent=i_agent)
for i_agent in range(args.n_manager)]
teacher = set_policy(env, tb_writer, log, args, name="teacher", i_agent=0)
assert len(workers) == len(managers), "The two number must be same"
assert len(managers) == len(temp_managers), "The two number must be same"
# Start train
train(
workers=workers, managers=managers,
temp_managers=temp_managers, teacher=teacher,
env=env, log=log, tb_writer=tb_writer, args=args)
def main(args):
# Create dir
if not os.path.exists("./logs"):
os.makedirs("./logs")
if not os.path.exists("./pytorch_models"):
os.makedirs("./pytorch_models")
# Set logs
tb_writer = SummaryWriter('./logs/tb_{0}'.format(args.log_name))
log = set_log(args)
# Create env
env = make_env(args)
# Set seeds
env.seed(args.seed)
torch.manual_seed(args.seed)
np.random.seed(args.seed)
# Initialize policy
predator_agents = [
set_policy(env, tb_writer, log, args, name="predator", i_agent=i_agent)
for i_agent in range(args.n_predator)
]
prey_agents = [
set_policy(env, tb_writer, log, args, name="prey", i_agent=i_agent)
for i_agent in range(args.n_prey)
]
# Start training
train(predator_agents=predator_agents,
prey_agents=prey_agents,
env=env,
log=log,
tb_writer=tb_writer,
args=args)
def main(args):
# Check arguments
assert args.n_agent == 2, "Only two agents are supported"
# Create directories
if not os.path.exists("./logs"):
os.makedirs("./logs")
if not os.path.exists("./data"):
os.makedirs("./data")
# Set logs
tb_writer = SummaryWriter('./logs/tb_{0}'.format(args.log_name))
log = set_log(args)
# Create env
env = make_env(args)
# Set seeds
env.seed(args.seed)
np.random.seed(args.seed)
# Set agents
agents = [
Agent(env=env,
tb_writer=tb_writer,
log=log,
args=args,
name="agent",
i_agent=i_agent) for i_agent in range(args.n_agent)
]
# Get true return by Monte Carlo estimate
if args.estimate_option == "montecarlo":
from trainer.montecarlo import train
table = train(agents=agents,
env=env,
log=log,
tb_writer=tb_writer,
args=args)
elif args.estimate_option == "naive":
from trainer.naive import train
table = train(agents=agents,
env=env,
log=log,
tb_writer=tb_writer,
args=args)
elif args.estimate_option == "ours":
from trainer.ours_mp import train
# from trainer.ours import train
table = train(agents=agents,
env=env,
log=log,
tb_writer=tb_writer,
args=args)
else:
raise ValueError("Invalid option")
# Save and vis result
save_name = args.estimate_option + "_" + str(args.decay_max_timesteps)
if args.estimate_option == "ours":
save_name += "_" + str(args.future_max_timesteps)
np.save("./data/" + save_name + ".npy", table)
