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;
157 lines
6.4 KiB
Python
157 lines
6.4 KiB
Python
import os
|
|
import gym
|
|
import torch
|
|
import pprint
|
|
import datetime
|
|
import argparse
|
|
import numpy as np
|
|
from torch.utils.tensorboard import SummaryWriter
|
|
|
|
from tianshou.policy import SACPolicy
|
|
from tianshou.utils import BasicLogger
|
|
from tianshou.env import SubprocVectorEnv
|
|
from tianshou.utils.net.common import Net
|
|
from tianshou.trainer import offpolicy_trainer
|
|
from tianshou.data import Collector, VectorReplayBuffer
|
|
from tianshou.utils.net.continuous import ActorProb, Critic
|
|
|
|
|
|
def get_args():
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument('--task', type=str, default='Ant-v3')
|
|
parser.add_argument('--seed', type=int, default=1626)
|
|
parser.add_argument('--buffer-size', type=int, default=1000000)
|
|
parser.add_argument('--actor-lr', type=float, default=3e-4)
|
|
parser.add_argument('--critic-lr', type=float, default=3e-4)
|
|
parser.add_argument('--gamma', type=float, default=0.99)
|
|
parser.add_argument('--tau', type=float, default=0.005)
|
|
parser.add_argument('--alpha', type=float, default=0.2)
|
|
parser.add_argument('--auto-alpha', default=False, action='store_true')
|
|
parser.add_argument('--alpha-lr', type=float, default=3e-4)
|
|
parser.add_argument('--n-step', type=int, default=2)
|
|
parser.add_argument('--epoch', type=int, default=100)
|
|
parser.add_argument('--step-per-epoch', type=int, default=40000)
|
|
parser.add_argument('--step-per-collect', type=int, default=4)
|
|
parser.add_argument('--update-per-step', type=float, default=0.25)
|
|
parser.add_argument('--update-per-step', type=int, default=1)
|
|
parser.add_argument('--pre-collect-step', type=int, default=10000)
|
|
parser.add_argument('--batch-size', type=int, default=256)
|
|
parser.add_argument('--hidden-sizes', type=int,
|
|
nargs='*', default=[128, 128])
|
|
parser.add_argument('--training-num', type=int, default=4)
|
|
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('--log-interval', type=int, default=1000)
|
|
parser.add_argument(
|
|
'--device', type=str,
|
|
default='cuda' if torch.cuda.is_available() else 'cpu')
|
|
parser.add_argument('--resume-path', type=str, default=None)
|
|
parser.add_argument('--watch', default=False, action='store_true',
|
|
help='watch the play of pre-trained policy only')
|
|
return parser.parse_args()
|
|
|
|
|
|
def test_sac(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]
|
|
print("Observations shape:", args.state_shape)
|
|
print("Actions shape:", args.action_shape)
|
|
print("Action range:", np.min(env.action_space.low),
|
|
np.max(env.action_space.high))
|
|
# 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.state_shape, hidden_sizes=args.hidden_sizes,
|
|
device=args.device)
|
|
actor = ActorProb(
|
|
net, args.action_shape, max_action=args.max_action,
|
|
device=args.device, unbounded=True, conditioned_sigma=True
|
|
).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)
|
|
|
|
if args.auto_alpha:
|
|
target_entropy = -np.prod(env.action_space.shape)
|
|
log_alpha = torch.zeros(1, requires_grad=True, device=args.device)
|
|
alpha_optim = torch.optim.Adam([log_alpha], lr=args.alpha_lr)
|
|
args.alpha = (target_entropy, log_alpha, alpha_optim)
|
|
|
|
policy = SACPolicy(
|
|
actor, actor_optim, critic1, critic1_optim, critic2, critic2_optim,
|
|
action_range=[env.action_space.low[0], env.action_space.high[0]],
|
|
tau=args.tau, gamma=args.gamma, alpha=args.alpha,
|
|
estimation_step=args.n_step)
|
|
# load a previous policy
|
|
if args.resume_path:
|
|
policy.load_state_dict(torch.load(
|
|
args.resume_path, map_location=args.device
|
|
))
|
|
print("Loaded agent from: ", args.resume_path)
|
|
|
|
# collector
|
|
train_collector = Collector(
|
|
policy, train_envs,
|
|
VectorReplayBuffer(args.buffer_size, len(train_envs)),
|
|
exploration_noise=True)
|
|
test_collector = Collector(policy, test_envs)
|
|
# log
|
|
log_path = os.path.join(args.logdir, args.task, 'sac', 'seed_' + str(
|
|
args.seed) + '_' + datetime.datetime.now().strftime('%m%d-%H%M%S'))
|
|
writer = SummaryWriter(log_path)
|
|
writer.add_text("args", str(args))
|
|
logger = BasicLogger(writer, train_interval=args.log_interval)
|
|
|
|
def watch():
|
|
# watch agent's performance
|
|
print("Testing agent ...")
|
|
policy.eval()
|
|
test_envs.seed(args.seed)
|
|
test_collector.reset()
|
|
result = test_collector.collect(n_episode=args.test_num, render=args.render)
|
|
pprint.pprint(result)
|
|
|
|
def save_fn(policy):
|
|
torch.save(policy.state_dict(), os.path.join(log_path, 'policy.pth'))
|
|
|
|
def stop_fn(mean_rewards):
|
|
return False
|
|
|
|
if args.watch:
|
|
watch()
|
|
exit(0)
|
|
|
|
# trainer
|
|
train_collector.collect(n_step=args.pre_collect_step, random=True)
|
|
result = offpolicy_trainer(
|
|
policy, train_collector, test_collector, args.epoch,
|
|
args.step_per_epoch, args.step_per_collect, args.test_num,
|
|
args.batch_size, stop_fn=stop_fn, save_fn=save_fn, logger=logger,
|
|
update_per_step=args.update_per_step)
|
|
pprint.pprint(result)
|
|
watch()
|
|
|
|
|
|
if __name__ == '__main__':
|
|
test_sac()
|