150d0ec51b
This is the third PR of 6 commits mentioned in #274, which features refactor of Collector to fix #245. You can check #274 for more detail. Things changed in this PR: 1. refactor collector to be more cleaner, split AsyncCollector to support asyncvenv; 2. change buffer.add api to add(batch, bffer_ids); add several types of buffer (VectorReplayBuffer, PrioritizedVectorReplayBuffer, etc.) 3. add policy.exploration_noise(act, batch) -> act 4. small change in BasePolicy.compute_*_returns 5. move reward_metric from collector to trainer 6. fix np.asanyarray issue (different version's numpy will result in different output) 7. flake8 maxlength=88 8. polish docs and fix test Co-authored-by: n+e <trinkle23897@gmail.com>
146 lines
6.0 KiB
Python
146 lines
6.0 KiB
Python
import os
|
|
import gym
|
|
import torch
|
|
import pprint
|
|
import argparse
|
|
import numpy as np
|
|
from torch.utils.tensorboard import SummaryWriter
|
|
|
|
from tianshou.env import DummyVectorEnv
|
|
from tianshou.utils.net.common import Net
|
|
from tianshou.data import Collector, VectorReplayBuffer
|
|
from tianshou.utils.net.discrete import Actor, Critic
|
|
from tianshou.policy import A2CPolicy, ImitationPolicy
|
|
from tianshou.trainer import onpolicy_trainer, offpolicy_trainer
|
|
|
|
|
|
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('--buffer-size', type=int, default=20000)
|
|
parser.add_argument('--lr', type=float, default=3e-4)
|
|
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=1000)
|
|
parser.add_argument('--collect-per-step', type=int, default=8)
|
|
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=[128, 128, 128])
|
|
parser.add_argument('--imitation-hidden-sizes', type=int,
|
|
nargs='*', default=[128])
|
|
parser.add_argument('--training-num', type=int, default=8)
|
|
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', type=bool, default=False)
|
|
args = parser.parse_known_args()[0]
|
|
return args
|
|
|
|
|
|
def test_a2c_with_il(args=get_args()):
|
|
torch.set_num_threads(1) # for poor CPU
|
|
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
|
|
# you can also use tianshou.env.SubprocVectorEnv
|
|
# train_envs = gym.make(args.task)
|
|
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 = 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(set(
|
|
actor.parameters()).union(critic.parameters()), lr=args.lr)
|
|
dist = torch.distributions.Categorical
|
|
policy = A2CPolicy(
|
|
actor, critic, optim, dist, 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)
|
|
# 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, 'a2c')
|
|
writer = SummaryWriter(log_path)
|
|
|
|
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
|
|
|
|
# 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, save_fn=save_fn,
|
|
writer=writer)
|
|
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, mode='discrete')
|
|
il_test_collector = Collector(
|
|
il_policy,
|
|
DummyVectorEnv(
|
|
[lambda: gym.make(args.task) for _ in range(args.test_num)])
|
|
)
|
|
train_collector.reset()
|
|
result = offpolicy_trainer(
|
|
il_policy, train_collector, il_test_collector, args.epoch,
|
|
args.step_per_epoch, args.collect_per_step, args.test_num,
|
|
args.batch_size, stop_fn=stop_fn, save_fn=save_fn, writer=writer)
|
|
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()
|