1423eeb3b2
- Fix the current bug discussed in #844 in `test_ppo.py`. - Add warning for `ActorProb ` if both `max_action ` and `unbounded=True` are used for model initializations. - Add warning for PGpolicy and DDPGpolicy if they find duplicate usage of action-bounded actor and action scaling method.
205 lines
7.5 KiB
Python
205 lines
7.5 KiB
Python
import argparse
|
|
import os
|
|
import pprint
|
|
|
|
import gymnasium as gym
|
|
import numpy as np
|
|
import torch
|
|
from torch.distributions import Independent, Normal
|
|
from torch.utils.tensorboard import SummaryWriter
|
|
|
|
from tianshou.data import Collector, VectorReplayBuffer
|
|
from tianshou.env import DummyVectorEnv
|
|
from tianshou.policy import PPOPolicy
|
|
from tianshou.trainer import OnpolicyTrainer
|
|
from tianshou.utils import TensorboardLogger
|
|
from tianshou.utils.net.common import ActorCritic, Net
|
|
from tianshou.utils.net.continuous import ActorProb, 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('--lr', type=float, default=1e-3)
|
|
parser.add_argument('--gamma', type=float, default=0.95)
|
|
parser.add_argument('--epoch', type=int, default=5)
|
|
parser.add_argument('--step-per-epoch', type=int, default=150000)
|
|
parser.add_argument('--episode-per-collect', type=int, default=16)
|
|
parser.add_argument('--repeat-per-collect', type=int, default=2)
|
|
parser.add_argument('--batch-size', type=int, default=128)
|
|
parser.add_argument('--hidden-sizes', type=int, nargs='*', default=[64, 64])
|
|
parser.add_argument('--training-num', type=int, default=16)
|
|
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'
|
|
)
|
|
# ppo special
|
|
parser.add_argument('--vf-coef', type=float, default=0.25)
|
|
parser.add_argument('--ent-coef', type=float, default=0.0)
|
|
parser.add_argument('--eps-clip', type=float, default=0.2)
|
|
parser.add_argument('--max-grad-norm', type=float, default=0.5)
|
|
parser.add_argument('--gae-lambda', type=float, default=0.95)
|
|
parser.add_argument('--rew-norm', type=int, default=1)
|
|
parser.add_argument('--dual-clip', type=float, default=None)
|
|
parser.add_argument('--value-clip', type=int, default=1)
|
|
parser.add_argument('--norm-adv', type=int, default=1)
|
|
parser.add_argument('--recompute-adv', type=int, default=0)
|
|
parser.add_argument('--resume', action="store_true")
|
|
parser.add_argument("--save-interval", type=int, default=4)
|
|
args = parser.parse_known_args()[0]
|
|
return args
|
|
|
|
|
|
def test_ppo(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 = ActorProb(net, args.action_shape, unbounded=True,
|
|
device=args.device).to(args.device)
|
|
critic = Critic(
|
|
Net(args.state_shape, hidden_sizes=args.hidden_sizes, device=args.device),
|
|
device=args.device
|
|
).to(args.device)
|
|
actor_critic = ActorCritic(actor, critic)
|
|
# orthogonal initialization
|
|
for m in actor_critic.modules():
|
|
if isinstance(m, torch.nn.Linear):
|
|
torch.nn.init.orthogonal_(m.weight)
|
|
torch.nn.init.zeros_(m.bias)
|
|
optim = torch.optim.Adam(actor_critic.parameters(), lr=args.lr)
|
|
|
|
# replace DiagGuassian with Independent(Normal) which is equivalent
|
|
# pass *logits to be consistent with policy.forward
|
|
def dist(*logits):
|
|
return Independent(Normal(*logits), 1)
|
|
|
|
policy = PPOPolicy(
|
|
actor,
|
|
critic,
|
|
optim,
|
|
dist,
|
|
discount_factor=args.gamma,
|
|
max_grad_norm=args.max_grad_norm,
|
|
eps_clip=args.eps_clip,
|
|
vf_coef=args.vf_coef,
|
|
ent_coef=args.ent_coef,
|
|
reward_normalization=args.rew_norm,
|
|
advantage_normalization=args.norm_adv,
|
|
recompute_advantage=args.recompute_adv,
|
|
dual_clip=args.dual_clip,
|
|
value_clip=args.value_clip,
|
|
gae_lambda=args.gae_lambda,
|
|
action_space=env.action_space,
|
|
)
|
|
# collector
|
|
train_collector = Collector(
|
|
policy, train_envs, VectorReplayBuffer(args.buffer_size, len(train_envs))
|
|
)
|
|
test_collector = Collector(policy, test_envs)
|
|
# log
|
|
log_path = os.path.join(args.logdir, args.task, "ppo")
|
|
writer = SummaryWriter(log_path)
|
|
logger = TensorboardLogger(writer, save_interval=args.save_interval)
|
|
|
|
def save_best_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
|
|
|
|
def save_checkpoint_fn(epoch, env_step, gradient_step):
|
|
# see also: https://pytorch.org/tutorials/beginner/saving_loading_models.html
|
|
ckpt_path = os.path.join(log_path, "checkpoint.pth")
|
|
# Example: saving by epoch num
|
|
# ckpt_path = os.path.join(log_path, f"checkpoint_{epoch}.pth")
|
|
torch.save(
|
|
{
|
|
"model": policy.state_dict(),
|
|
"optim": optim.state_dict(),
|
|
}, ckpt_path
|
|
)
|
|
return ckpt_path
|
|
|
|
if args.resume:
|
|
# load from existing checkpoint
|
|
print(f"Loading agent under {log_path}")
|
|
ckpt_path = os.path.join(log_path, "checkpoint.pth")
|
|
if os.path.exists(ckpt_path):
|
|
checkpoint = torch.load(ckpt_path, map_location=args.device)
|
|
policy.load_state_dict(checkpoint["model"])
|
|
optim.load_state_dict(checkpoint["optim"])
|
|
print("Successfully restore policy and optim.")
|
|
else:
|
|
print("Fail to restore policy and optim.")
|
|
|
|
# trainer
|
|
trainer = OnpolicyTrainer(
|
|
policy,
|
|
train_collector,
|
|
test_collector,
|
|
args.epoch,
|
|
args.step_per_epoch,
|
|
args.repeat_per_collect,
|
|
args.test_num,
|
|
args.batch_size,
|
|
episode_per_collect=args.episode_per_collect,
|
|
stop_fn=stop_fn,
|
|
save_best_fn=save_best_fn,
|
|
logger=logger,
|
|
resume_from_log=args.resume,
|
|
save_checkpoint_fn=save_checkpoint_fn,
|
|
)
|
|
|
|
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()}")
|
|
|
|
|
|
def test_ppo_resume(args=get_args()):
|
|
args.resume = True
|
|
test_ppo(args)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
test_ppo()
|