193 lines
6.8 KiB
Python
Executable File
193 lines
6.8 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
|
|
import argparse
|
|
import datetime
|
|
import os
|
|
import pprint
|
|
|
|
import gym
|
|
import numpy as np
|
|
import torch
|
|
from torch.utils.tensorboard import SummaryWriter
|
|
|
|
from tianshou.data import Collector, ReplayBuffer, VectorReplayBuffer
|
|
from tianshou.env import SubprocVectorEnv
|
|
from tianshou.policy import REDQPolicy
|
|
from tianshou.trainer import offpolicy_trainer
|
|
from tianshou.utils import TensorboardLogger
|
|
from tianshou.utils.net.common import EnsembleLinear, Net
|
|
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=0)
|
|
parser.add_argument('--buffer-size', type=int, default=1000000)
|
|
parser.add_argument('--hidden-sizes', type=int, nargs='*', default=[256, 256])
|
|
parser.add_argument('--ensemble-size', type=int, default=10)
|
|
parser.add_argument('--subset-size', type=int, default=2)
|
|
parser.add_argument('--actor-lr', type=float, default=1e-3)
|
|
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('--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("--start-timesteps", type=int, default=10000)
|
|
parser.add_argument('--epoch', type=int, default=200)
|
|
parser.add_argument('--step-per-epoch', type=int, default=5000)
|
|
parser.add_argument('--step-per-collect', type=int, default=1)
|
|
parser.add_argument('--update-per-step', type=int, default=20)
|
|
parser.add_argument('--n-step', type=int, default=1)
|
|
parser.add_argument('--batch-size', type=int, default=256)
|
|
parser.add_argument(
|
|
'--target-mode', type=str, choices=('min', 'mean'), default='min'
|
|
)
|
|
parser.add_argument('--training-num', type=int, default=1)
|
|
parser.add_argument('--test-num', type=int, default=10)
|
|
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'
|
|
)
|
|
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_redq(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)
|
|
if args.training_num > 1:
|
|
train_envs = SubprocVectorEnv(
|
|
[lambda: gym.make(args.task) for _ in range(args.training_num)]
|
|
)
|
|
else:
|
|
train_envs = gym.make(args.task)
|
|
# 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_a = Net(args.state_shape, hidden_sizes=args.hidden_sizes, device=args.device)
|
|
actor = ActorProb(
|
|
net_a,
|
|
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)
|
|
|
|
def linear(x, y):
|
|
return EnsembleLinear(args.ensemble_size, x, y)
|
|
|
|
net_c = Net(
|
|
args.state_shape,
|
|
args.action_shape,
|
|
hidden_sizes=args.hidden_sizes,
|
|
concat=True,
|
|
device=args.device,
|
|
linear_layer=linear,
|
|
)
|
|
critics = Critic(
|
|
net_c,
|
|
device=args.device,
|
|
linear_layer=linear,
|
|
flatten_input=False,
|
|
).to(args.device)
|
|
critics_optim = torch.optim.Adam(critics.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 = REDQPolicy(
|
|
actor,
|
|
actor_optim,
|
|
critics,
|
|
critics_optim,
|
|
args.ensemble_size,
|
|
args.subset_size,
|
|
tau=args.tau,
|
|
gamma=args.gamma,
|
|
alpha=args.alpha,
|
|
estimation_step=args.n_step,
|
|
actor_delay=args.update_per_step,
|
|
target_mode=args.target_mode,
|
|
action_space=env.action_space,
|
|
)
|
|
|
|
# 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
|
|
if args.training_num > 1:
|
|
buffer = VectorReplayBuffer(args.buffer_size, len(train_envs))
|
|
else:
|
|
buffer = ReplayBuffer(args.buffer_size)
|
|
train_collector = Collector(policy, train_envs, buffer, exploration_noise=True)
|
|
test_collector = Collector(policy, test_envs)
|
|
train_collector.collect(n_step=args.start_timesteps, random=True)
|
|
# log
|
|
t0 = datetime.datetime.now().strftime("%m%d_%H%M%S")
|
|
log_file = f'seed_{args.seed}_{t0}-{args.task.replace("-", "_")}_redq'
|
|
log_path = os.path.join(args.logdir, args.task, 'redq', log_file)
|
|
writer = SummaryWriter(log_path)
|
|
writer.add_text("args", str(args))
|
|
logger = TensorboardLogger(writer)
|
|
|
|
def save_best_fn(policy):
|
|
torch.save(policy.state_dict(), os.path.join(log_path, 'policy.pth'))
|
|
|
|
if not args.watch:
|
|
# 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,
|
|
save_best_fn=save_best_fn,
|
|
logger=logger,
|
|
update_per_step=args.update_per_step,
|
|
test_in_train=False
|
|
)
|
|
pprint.pprint(result)
|
|
|
|
# Let's watch its performance!
|
|
policy.eval()
|
|
test_envs.seed(args.seed)
|
|
test_collector.reset()
|
|
result = test_collector.collect(n_episode=args.test_num, render=args.render)
|
|
print(f'Final reward: {result["rews"].mean()}, length: {result["lens"].mean()}')
|
|
|
|
|
|
if __name__ == '__main__':
|
|
test_redq()
|