9b61bc620c
This PR focus on refactor of logging method to solve bug of nan reward and log interval. After these two pr, hopefully fundamental change of tianshou/data is finished. We then can concentrate on building benchmarks of tianshou finally. Things changed: 1. trainer now accepts logger (BasicLogger or LazyLogger) instead of writer; 2. remove utils.SummaryWriter;
117 lines
4.6 KiB
Python
117 lines
4.6 KiB
Python
import os
|
|
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.utils import BasicLogger
|
|
from tianshou.env import DummyVectorEnv
|
|
from tianshou.trainer import offpolicy_trainer
|
|
from tianshou.utils.net.common import Recurrent
|
|
from tianshou.data import Collector, VectorReplayBuffer
|
|
|
|
|
|
def get_args():
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument('--task', type=str, default='CartPole-v0')
|
|
parser.add_argument('--seed', type=int, default=1)
|
|
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('--stack-num', type=int, default=4)
|
|
parser.add_argument('--lr', type=float, default=1e-3)
|
|
parser.add_argument('--gamma', type=float, default=0.95)
|
|
parser.add_argument('--n-step', type=int, default=4)
|
|
parser.add_argument('--target-update-freq', type=int, default=320)
|
|
parser.add_argument('--epoch', type=int, default=10)
|
|
parser.add_argument('--step-per-epoch', type=int, default=10000)
|
|
parser.add_argument('--update-per-step', type=float, default=0.1)
|
|
parser.add_argument('--step-per-collect', 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=10)
|
|
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_drqn(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)
|
|
# you can also use tianshou.env.SubprocVectorEnv
|
|
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 = Recurrent(args.layer_num, args.state_shape,
|
|
args.action_shape, args.device).to(args.device)
|
|
optim = torch.optim.Adam(net.parameters(), lr=args.lr)
|
|
policy = DQNPolicy(
|
|
net, optim, args.gamma, args.n_step,
|
|
target_update_freq=args.target_update_freq)
|
|
# collector
|
|
buffer = VectorReplayBuffer(
|
|
args.buffer_size, buffer_num=len(train_envs),
|
|
stack_num=args.stack_num, ignore_obs_next=True)
|
|
train_collector = Collector(policy, train_envs, buffer, exploration_noise=True)
|
|
# the stack_num is for RNN training: sample framestack obs
|
|
test_collector = Collector(policy, test_envs, exploration_noise=True)
|
|
# policy.set_eps(1)
|
|
train_collector.collect(n_step=args.batch_size * args.training_num)
|
|
# log
|
|
log_path = os.path.join(args.logdir, args.task, 'drqn')
|
|
writer = SummaryWriter(log_path)
|
|
logger = BasicLogger(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 >= env.spec.reward_threshold
|
|
|
|
def train_fn(epoch, env_step):
|
|
policy.set_eps(args.eps_train)
|
|
|
|
def test_fn(epoch, env_step):
|
|
policy.set_eps(args.eps_test)
|
|
|
|
# trainer
|
|
result = offpolicy_trainer(
|
|
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,
|
|
train_fn=train_fn, test_fn=test_fn, stop_fn=stop_fn,
|
|
save_fn=save_fn, logger=logger)
|
|
|
|
assert stop_fn(result['best_reward'])
|
|
if __name__ == '__main__':
|
|
pprint.pprint(result)
|
|
# 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_drqn(get_args())
|