173 lines
6.5 KiB
Python
173 lines
6.5 KiB
Python
import argparse
|
|
import os
|
|
import pprint
|
|
|
|
import envpool
|
|
import gym
|
|
import numpy as np
|
|
import torch
|
|
from torch.utils.tensorboard import SummaryWriter
|
|
|
|
from tianshou.data import Collector, VectorReplayBuffer
|
|
from tianshou.policy import A2CPolicy, ImitationPolicy
|
|
from tianshou.trainer import offpolicy_trainer, onpolicy_trainer
|
|
from tianshou.utils import TensorboardLogger
|
|
from tianshou.utils.net.common import ActorCritic, Net
|
|
from tianshou.utils.net.discrete import Actor, Critic
|
|
|
|
|
|
def get_args():
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument('--task', type=str, default='CartPole-v0')
|
|
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('--il-lr', type=float, default=1e-3)
|
|
parser.add_argument('--gamma', type=float, default=0.9)
|
|
parser.add_argument('--epoch', type=int, default=10)
|
|
parser.add_argument('--step-per-epoch', type=int, default=50000)
|
|
parser.add_argument('--il-step-per-epoch', type=int, default=1000)
|
|
parser.add_argument('--episode-per-collect', type=int, default=16)
|
|
parser.add_argument('--step-per-collect', type=int, default=16)
|
|
parser.add_argument('--update-per-step', type=float, default=1 / 16)
|
|
parser.add_argument('--repeat-per-collect', type=int, default=1)
|
|
parser.add_argument('--batch-size', type=int, default=64)
|
|
parser.add_argument('--hidden-sizes', type=int, nargs='*', default=[64, 64])
|
|
parser.add_argument('--imitation-hidden-sizes', type=int, nargs='*', default=[128])
|
|
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'
|
|
)
|
|
# a2c special
|
|
parser.add_argument('--vf-coef', type=float, default=0.5)
|
|
parser.add_argument('--ent-coef', type=float, default=0.0)
|
|
parser.add_argument('--max-grad-norm', type=float, default=None)
|
|
parser.add_argument('--gae-lambda', type=float, default=1.)
|
|
parser.add_argument('--rew-norm', action="store_true", default=False)
|
|
args = parser.parse_known_args()[0]
|
|
return args
|
|
|
|
|
|
def test_a2c_with_il(args=get_args()):
|
|
train_envs = env = envpool.make_gym(
|
|
args.task, num_envs=args.training_num, seed=args.seed
|
|
)
|
|
test_envs = envpool.make_gym(args.task, num_envs=args.test_num, seed=args.seed)
|
|
args.state_shape = env.observation_space.shape or env.observation_space.n
|
|
args.action_shape = env.action_space.shape or env.action_space.n
|
|
if args.reward_threshold is None:
|
|
default_reward_threshold = {"CartPole-v0": 195}
|
|
args.reward_threshold = default_reward_threshold.get(
|
|
args.task, env.spec.reward_threshold
|
|
)
|
|
# seed
|
|
np.random.seed(args.seed)
|
|
torch.manual_seed(args.seed)
|
|
# model
|
|
net = Net(args.state_shape, hidden_sizes=args.hidden_sizes, device=args.device)
|
|
actor = Actor(net, args.action_shape, device=args.device).to(args.device)
|
|
critic = Critic(net, device=args.device).to(args.device)
|
|
optim = torch.optim.Adam(ActorCritic(actor, critic).parameters(), lr=args.lr)
|
|
dist = torch.distributions.Categorical
|
|
policy = A2CPolicy(
|
|
actor,
|
|
critic,
|
|
optim,
|
|
dist,
|
|
discount_factor=args.gamma,
|
|
gae_lambda=args.gae_lambda,
|
|
vf_coef=args.vf_coef,
|
|
ent_coef=args.ent_coef,
|
|
max_grad_norm=args.max_grad_norm,
|
|
reward_normalization=args.rew_norm,
|
|
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, 'a2c')
|
|
writer = SummaryWriter(log_path)
|
|
logger = TensorboardLogger(writer)
|
|
|
|
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
|
|
|
|
# trainer
|
|
result = onpolicy_trainer(
|
|
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
|
|
)
|
|
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()}")
|
|
|
|
policy.eval()
|
|
# here we define an imitation collector with a trivial policy
|
|
# if args.task == 'CartPole-v0':
|
|
# env.spec.reward_threshold = 190 # lower the goal
|
|
net = Net(args.state_shape, hidden_sizes=args.hidden_sizes, device=args.device)
|
|
net = Actor(net, args.action_shape, device=args.device).to(args.device)
|
|
optim = torch.optim.Adam(net.parameters(), lr=args.il_lr)
|
|
il_policy = ImitationPolicy(net, optim, action_space=env.action_space)
|
|
il_test_collector = Collector(
|
|
il_policy,
|
|
envpool.make_gym(args.task, num_envs=args.test_num, seed=args.seed),
|
|
)
|
|
train_collector.reset()
|
|
result = offpolicy_trainer(
|
|
il_policy,
|
|
train_collector,
|
|
il_test_collector,
|
|
args.epoch,
|
|
args.il_step_per_epoch,
|
|
args.step_per_collect,
|
|
args.test_num,
|
|
args.batch_size,
|
|
stop_fn=stop_fn,
|
|
save_best_fn=save_best_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)
|
|
il_policy.eval()
|
|
collector = Collector(il_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_a2c_with_il()
|