710966eda7
train_fn(epoch) -> train_fn(epoch, num_env_step) test_fn(epoch) -> test_fn(epoch, num_env_step)
119 lines
4.8 KiB
Python
119 lines
4.8 KiB
Python
import gym
|
|
import torch
|
|
import pprint
|
|
import argparse
|
|
import numpy as np
|
|
from torch.utils.tensorboard import SummaryWriter
|
|
|
|
from tianshou.policy import TD3Policy
|
|
from tianshou.utils.net.common import Net
|
|
from tianshou.env import SubprocVectorEnv
|
|
from tianshou.exploration import GaussianNoise
|
|
from tianshou.trainer import offpolicy_trainer
|
|
from tianshou.data import Collector, ReplayBuffer
|
|
from tianshou.utils.net.continuous import Actor, Critic
|
|
|
|
from mujoco.register import reg
|
|
|
|
|
|
def get_args():
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument('--task', type=str, default='PointMaze-v1')
|
|
parser.add_argument('--seed', type=int, default=1626)
|
|
parser.add_argument('--buffer-size', type=int, default=20000)
|
|
parser.add_argument('--actor-lr', type=float, default=3e-5)
|
|
parser.add_argument('--critic-lr', type=float, default=1e-4)
|
|
parser.add_argument('--gamma', type=float, default=0.99)
|
|
parser.add_argument('--tau', type=float, default=0.005)
|
|
parser.add_argument('--exploration-noise', type=float, default=0.1)
|
|
parser.add_argument('--policy-noise', type=float, default=0.2)
|
|
parser.add_argument('--noise-clip', type=float, default=0.5)
|
|
parser.add_argument('--update-actor-freq', type=int, default=2)
|
|
parser.add_argument('--epoch', type=int, default=100)
|
|
parser.add_argument('--step-per-epoch', type=int, default=2400)
|
|
parser.add_argument('--collect-per-step', type=int, default=10)
|
|
parser.add_argument('--batch-size', type=int, default=128)
|
|
parser.add_argument('--layer-num', type=int, default=1)
|
|
parser.add_argument('--training-num', type=int, default=8)
|
|
parser.add_argument('--test-num', type=int, default=100)
|
|
parser.add_argument('--logdir', type=str, default='log')
|
|
parser.add_argument('--render', type=float, default=0.)
|
|
parser.add_argument(
|
|
'--device', type=str,
|
|
default='cuda' if torch.cuda.is_available() else 'cpu')
|
|
return parser.parse_args()
|
|
|
|
|
|
def test_td3(args=get_args()):
|
|
reg()
|
|
env = gym.make(args.task)
|
|
args.state_shape = env.observation_space.shape or env.observation_space.n
|
|
args.action_shape = env.action_space.shape or env.action_space.n
|
|
args.max_action = env.action_space.high[0]
|
|
# train_envs = gym.make(args.task)
|
|
train_envs = SubprocVectorEnv(
|
|
[lambda: gym.make(args.task) for _ in range(args.training_num)])
|
|
# test_envs = gym.make(args.task)
|
|
test_envs = SubprocVectorEnv(
|
|
[lambda: gym.make(args.task) for _ in range(args.test_num)])
|
|
# seed
|
|
np.random.seed(args.seed)
|
|
torch.manual_seed(args.seed)
|
|
train_envs.seed(args.seed)
|
|
test_envs.seed(args.seed)
|
|
# model
|
|
net = Net(args.layer_num, args.state_shape, device=args.device)
|
|
actor = Actor(
|
|
net, args.action_shape,
|
|
args.max_action, args.device
|
|
).to(args.device)
|
|
actor_optim = torch.optim.Adam(actor.parameters(), lr=args.actor_lr)
|
|
net = Net(args.layer_num, args.state_shape,
|
|
args.action_shape, concat=True, device=args.device)
|
|
critic1 = Critic(net, args.device).to(args.device)
|
|
critic1_optim = torch.optim.Adam(critic1.parameters(), lr=args.critic_lr)
|
|
critic2 = Critic(net, args.device).to(args.device)
|
|
critic2_optim = torch.optim.Adam(critic2.parameters(), lr=args.critic_lr)
|
|
policy = TD3Policy(
|
|
actor, actor_optim, critic1, critic1_optim, critic2, critic2_optim,
|
|
action_range=[env.action_space.low[0], env.action_space.high[0]],
|
|
tau=args.tau, gamma=args.gamma,
|
|
exploration_noise=GaussianNoise(sigma=args.exploration_noise),
|
|
policy_noise=args.policy_noise,
|
|
update_actor_freq=args.update_actor_freq,
|
|
noise_clip=args.noise_clip,
|
|
reward_normalization=True, ignore_done=True)
|
|
# collector
|
|
train_collector = Collector(
|
|
policy, train_envs, ReplayBuffer(args.buffer_size))
|
|
test_collector = Collector(policy, test_envs)
|
|
# train_collector.collect(n_step=args.buffer_size)
|
|
# log
|
|
writer = SummaryWriter(args.logdir + '/' + 'td3')
|
|
|
|
def stop_fn(mean_rewards):
|
|
if env.spec.reward_threshold:
|
|
return mean_rewards >= env.spec.reward_threshold
|
|
else:
|
|
return False
|
|
|
|
# trainer
|
|
result = offpolicy_trainer(
|
|
policy, train_collector, test_collector, args.epoch,
|
|
args.step_per_epoch, args.collect_per_step, args.test_num,
|
|
args.batch_size, stop_fn=stop_fn, writer=writer)
|
|
assert stop_fn(result['best_reward'])
|
|
if __name__ == '__main__':
|
|
pprint.pprint(result)
|
|
# Let's watch its performance!
|
|
policy.eval()
|
|
test_envs.seed(args.seed)
|
|
test_collector.reset()
|
|
result = test_collector.collect(n_episode=[1] * args.test_num,
|
|
render=args.render)
|
|
print(f'Final reward: {result["rew"]}, length: {result["len"]}')
|
|
|
|
|
|
if __name__ == '__main__':
|
|
test_td3()
|