10d919052b
The new proposed feature is to have trainers as generators.
The usage pattern is:
```python
trainer = OnPolicyTrainer(...)
for epoch, epoch_stat, info in trainer:
print(f"Epoch: {epoch}")
print(epoch_stat)
print(info)
do_something_with_policy()
query_something_about_policy()
make_a_plot_with(epoch_stat)
display(info)
```
- epoch int: the epoch number
- epoch_stat dict: a large collection of metrics of the current epoch, including stat
- info dict: the usual dict out of the non-generator version of the trainer
You can even iterate on several different trainers at the same time:
```python
trainer1 = OnPolicyTrainer(...)
trainer2 = OnPolicyTrainer(...)
for result1, result2, ... in zip(trainer1, trainer2, ...):
compare_results(result1, result2, ...)
```
Co-authored-by: Jiayi Weng <trinkle23897@gmail.com>
173 lines
6.1 KiB
Python
173 lines
6.1 KiB
Python
import argparse
|
|
import os
|
|
import pprint
|
|
|
|
import gym
|
|
import numpy as np
|
|
import torch
|
|
from torch.utils.tensorboard import SummaryWriter
|
|
|
|
from tianshou.data import Collector, VectorReplayBuffer
|
|
from tianshou.env import DummyVectorEnv
|
|
from tianshou.exploration import GaussianNoise
|
|
from tianshou.policy import TD3Policy
|
|
from tianshou.trainer import OffpolicyTrainer
|
|
from tianshou.utils import TensorboardLogger
|
|
from tianshou.utils.net.common import Net
|
|
from tianshou.utils.net.continuous import Actor, Critic
|
|
|
|
|
|
def get_args():
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument('--task', type=str, default='Pendulum-v1')
|
|
parser.add_argument('--reward-threshold', type=float, default=None)
|
|
parser.add_argument('--seed', type=int, default=1)
|
|
parser.add_argument('--buffer-size', type=int, default=20000)
|
|
parser.add_argument('--actor-lr', type=float, default=1e-4)
|
|
parser.add_argument('--critic-lr', type=float, default=1e-3)
|
|
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=5)
|
|
parser.add_argument('--step-per-epoch', type=int, default=20000)
|
|
parser.add_argument('--step-per-collect', type=int, default=8)
|
|
parser.add_argument('--update-per-step', type=float, default=0.125)
|
|
parser.add_argument('--batch-size', type=int, default=128)
|
|
parser.add_argument('--hidden-sizes', type=int, nargs='*', default=[128, 128])
|
|
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('--rew-norm', action="store_true", default=False)
|
|
parser.add_argument('--n-step', type=int, default=3)
|
|
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_td3(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
|
|
args.max_action = env.action_space.high[0]
|
|
if args.reward_threshold is None:
|
|
default_reward_threshold = {"Pendulum-v0": -250, "Pendulum-v1": -250}
|
|
args.reward_threshold = default_reward_threshold.get(
|
|
args.task, env.spec.reward_threshold
|
|
)
|
|
# you can also use tianshou.env.SubprocVectorEnv
|
|
# train_envs = gym.make(args.task)
|
|
train_envs = DummyVectorEnv(
|
|
[lambda: gym.make(args.task) for _ in range(args.training_num)]
|
|
)
|
|
# test_envs = gym.make(args.task)
|
|
test_envs = DummyVectorEnv(
|
|
[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.state_shape, hidden_sizes=args.hidden_sizes, device=args.device)
|
|
actor = Actor(
|
|
net, args.action_shape, max_action=args.max_action, device=args.device
|
|
).to(args.device)
|
|
actor_optim = torch.optim.Adam(actor.parameters(), lr=args.actor_lr)
|
|
net_c1 = Net(
|
|
args.state_shape,
|
|
args.action_shape,
|
|
hidden_sizes=args.hidden_sizes,
|
|
concat=True,
|
|
device=args.device
|
|
)
|
|
critic1 = Critic(net_c1, device=args.device).to(args.device)
|
|
critic1_optim = torch.optim.Adam(critic1.parameters(), lr=args.critic_lr)
|
|
net_c2 = Net(
|
|
args.state_shape,
|
|
args.action_shape,
|
|
hidden_sizes=args.hidden_sizes,
|
|
concat=True,
|
|
device=args.device
|
|
)
|
|
critic2 = Critic(net_c2, device=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,
|
|
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=args.rew_norm,
|
|
estimation_step=args.n_step,
|
|
action_space=env.action_space
|
|
)
|
|
# collector
|
|
train_collector = Collector(
|
|
policy,
|
|
train_envs,
|
|
VectorReplayBuffer(args.buffer_size, len(train_envs)),
|
|
exploration_noise=True
|
|
)
|
|
test_collector = Collector(policy, test_envs)
|
|
# train_collector.collect(n_step=args.buffer_size)
|
|
# log
|
|
log_path = os.path.join(args.logdir, args.task, 'td3')
|
|
writer = SummaryWriter(log_path)
|
|
logger = TensorboardLogger(writer)
|
|
|
|
def save_fn(policy):
|
|
torch.save(policy.state_dict(), os.path.join(log_path, 'policy.pth'))
|
|
|
|
def stop_fn(mean_rewards):
|
|
return mean_rewards >= args.reward_threshold
|
|
|
|
# Iterator trainer
|
|
trainer = OffpolicyTrainer(
|
|
policy,
|
|
train_collector,
|
|
test_collector,
|
|
args.epoch,
|
|
args.step_per_epoch,
|
|
args.step_per_collect,
|
|
args.test_num,
|
|
args.batch_size,
|
|
update_per_step=args.update_per_step,
|
|
stop_fn=stop_fn,
|
|
save_fn=save_fn,
|
|
logger=logger,
|
|
)
|
|
for epoch, epoch_stat, info in trainer:
|
|
print(f"Epoch: {epoch}")
|
|
print(epoch_stat)
|
|
print(info)
|
|
|
|
assert stop_fn(info["best_reward"])
|
|
|
|
if __name__ == "__main__":
|
|
pprint.pprint(info)
|
|
# Let's watch its performance!
|
|
env = gym.make(args.task)
|
|
policy.eval()
|
|
collector = Collector(policy, env)
|
|
result = collector.collect(n_episode=1, render=args.render)
|
|
rews, lens = result["rews"], result["lens"]
|
|
print(f"Final reward: {rews.mean()}, length: {lens.mean()}")
|
|
|
|
|
|
if __name__ == '__main__':
|
|
test_td3()
|