117 lines
4.4 KiB
Python
117 lines
4.4 KiB
Python
import gym
|
|
import torch
|
|
import pprint
|
|
import argparse
|
|
import numpy as np
|
|
from torch.utils.tensorboard import SummaryWriter
|
|
|
|
from tianshou.policy import PPOPolicy
|
|
from tianshou.env import VectorEnv
|
|
from tianshou.trainer import onpolicy_trainer
|
|
from tianshou.data import Collector, ReplayBuffer
|
|
|
|
if __name__ == '__main__':
|
|
from net import ActorProb, Critic
|
|
else: # pytest
|
|
from test.continuous.net import ActorProb, Critic
|
|
|
|
|
|
def get_args():
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument('--task', type=str, default='Pendulum-v0')
|
|
parser.add_argument('--seed', type=int, default=0)
|
|
parser.add_argument('--buffer-size', type=int, default=20000)
|
|
parser.add_argument('--lr', type=float, default=3e-4)
|
|
parser.add_argument('--gamma', type=float, default=0.9)
|
|
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('--repeat-per-collect', type=int, default=2)
|
|
parser.add_argument('--batch-size', type=int, default=64)
|
|
parser.add_argument('--layer-num', type=int, default=1)
|
|
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=0.5)
|
|
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)
|
|
args = parser.parse_known_args()[0]
|
|
return args
|
|
|
|
|
|
def _test_ppo(args=get_args()):
|
|
# just a demo, I have not made it work :(
|
|
env = gym.make(args.task)
|
|
if args.task == 'Pendulum-v0':
|
|
env.spec.reward_threshold = -250
|
|
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]
|
|
# you can also use tianshou.env.SubprocVectorEnv
|
|
# train_envs = gym.make(args.task)
|
|
train_envs = VectorEnv(
|
|
[lambda: gym.make(args.task) for _ in range(args.training_num)])
|
|
# test_envs = gym.make(args.task)
|
|
test_envs = VectorEnv(
|
|
[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
|
|
actor = ActorProb(
|
|
args.layer_num, args.state_shape, args.action_shape,
|
|
args.max_action, args.device
|
|
).to(args.device)
|
|
critic = Critic(
|
|
args.layer_num, args.state_shape, device=args.device
|
|
).to(args.device)
|
|
optim = torch.optim.Adam(list(
|
|
actor.parameters()) + list(critic.parameters()), lr=args.lr)
|
|
dist = torch.distributions.Normal
|
|
policy = PPOPolicy(
|
|
actor, critic, optim, dist, args.gamma,
|
|
max_grad_norm=args.max_grad_norm,
|
|
eps_clip=args.eps_clip,
|
|
vf_coef=args.vf_coef,
|
|
ent_coef=args.ent_coef,
|
|
action_range=[env.action_space.low[0], env.action_space.high[0]])
|
|
# collector
|
|
train_collector = Collector(
|
|
policy, train_envs, ReplayBuffer(args.buffer_size))
|
|
test_collector = Collector(policy, test_envs)
|
|
train_collector.collect(n_step=args.step_per_epoch)
|
|
# log
|
|
writer = SummaryWriter(args.logdir + '/' + 'ppo')
|
|
|
|
def stop_fn(x):
|
|
return x >= env.spec.reward_threshold
|
|
|
|
# trainer
|
|
result = onpolicy_trainer(
|
|
policy, train_collector, test_collector, args.epoch,
|
|
args.step_per_epoch, args.collect_per_step, args.repeat_per_collect,
|
|
args.test_num, args.batch_size, stop_fn=stop_fn, writer=writer)
|
|
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_ppo()
|