77068af526
* update atari.py * fix setup.py pass the pytest * fix setup.py pass the pytest * add args "render" * change the tensorboard writter * change the tensorboard writter * change device, render, tensorboard log location * change device, render, tensorboard log location * remove some wrong local files * fix some tab mistakes and the envs name in continuous/test_xx.py * add examples and point robot maze environment * fix some bugs during testing examples * add dqn network and fix some args * change back the tensorboard writter's frequency to ensure ppo and a2c can write things normally * add a warning to collector * rm some unrelated files * reformat * fix a bug in test_dqn due to the model wrong selection
110 lines
4.0 KiB
Python
110 lines
4.0 KiB
Python
import gym
|
|
import torch
|
|
import pprint
|
|
import argparse
|
|
import numpy as np
|
|
from torch.utils.tensorboard import SummaryWriter
|
|
|
|
from tianshou.policy import DQNPolicy
|
|
from tianshou.env import SubprocVectorEnv
|
|
from tianshou.trainer import offpolicy_trainer
|
|
from tianshou.data import Collector, ReplayBuffer
|
|
|
|
if __name__ == '__main__':
|
|
from net import Net
|
|
else: # pytest
|
|
from test.discrete.net import Net
|
|
|
|
|
|
def get_args():
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument('--task', type=str, default='CartPole-v0')
|
|
parser.add_argument('--seed', type=int, default=1626)
|
|
parser.add_argument('--eps-test', type=float, default=0.05)
|
|
parser.add_argument('--eps-train', type=float, default=0.1)
|
|
parser.add_argument('--buffer-size', type=int, default=20000)
|
|
parser.add_argument('--lr', type=float, default=1e-3)
|
|
parser.add_argument('--gamma', type=float, default=0.9)
|
|
parser.add_argument('--n-step', type=int, default=1)
|
|
parser.add_argument('--target-update-freq', type=int, default=320)
|
|
parser.add_argument('--epoch', type=int, default=100)
|
|
parser.add_argument('--step-per-epoch', type=int, default=1000)
|
|
parser.add_argument('--collect-per-step', type=int, default=10)
|
|
parser.add_argument('--batch-size', type=int, default=64)
|
|
parser.add_argument('--layer-num', type=int, default=3)
|
|
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')
|
|
args = parser.parse_known_args()[0]
|
|
return args
|
|
|
|
|
|
def test_dqn(args=get_args()):
|
|
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
|
|
# 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, args.action_shape, args.device)
|
|
net = net.to(args.device)
|
|
optim = torch.optim.Adam(net.parameters(), lr=args.lr)
|
|
policy = DQNPolicy(
|
|
net, optim, args.gamma, args.n_step,
|
|
use_target_network=args.target_update_freq > 0,
|
|
target_update_freq=args.target_update_freq)
|
|
# collector
|
|
train_collector = Collector(
|
|
policy, train_envs, ReplayBuffer(args.buffer_size))
|
|
test_collector = Collector(policy, test_envs)
|
|
# policy.set_eps(1)
|
|
train_collector.collect(n_step=args.batch_size)
|
|
print(len(train_collector.buffer))
|
|
# log
|
|
writer = SummaryWriter(args.logdir + '/' + 'ppo')
|
|
|
|
def stop_fn(x):
|
|
return x >= env.spec.reward_threshold
|
|
|
|
def train_fn(x):
|
|
policy.set_eps(args.eps_train)
|
|
|
|
def test_fn(x):
|
|
policy.set_eps(args.eps_test)
|
|
|
|
# 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, train_fn=train_fn, test_fn=test_fn,
|
|
stop_fn=stop_fn, writer=writer, task=args.task)
|
|
|
|
assert stop_fn(result['best_reward'])
|
|
train_collector.close()
|
|
test_collector.close()
|
|
if __name__ == '__main__':
|
|
pprint.pprint(result)
|
|
# Let's watch its performance!
|
|
env = gym.make(args.task)
|
|
collector = Collector(policy, env)
|
|
result = collector.collect(n_episode=1, render=args.render)
|
|
print(f'Final reward: {result["rew"]}, length: {result["len"]}')
|
|
collector.close()
|
|
|
|
|
|
if __name__ == '__main__':
|
|
test_dqn(get_args())
|