import gym
import torch
import pprint
import argparse
import numpy as np
from torch import nn
from torch.utils.tensorboard import SummaryWriter

from tianshou.policy import DQNPolicy
from tianshou.env import SubprocVectorEnv
from tianshou.trainer import offpolicy_trainer
from tianshou.data import Collector, ReplayBuffer


class Net(nn.Module):
    def __init__(self, layer_num, state_shape, action_shape, device='cpu'):
        super().__init__()
        self.device = device
        self.model = [
            nn.Linear(np.prod(state_shape), 128),
            nn.ReLU(inplace=True)]
        for i in range(layer_num):
            self.model += [nn.Linear(128, 128), nn.ReLU(inplace=True)]
        self.model += [nn.Linear(128, np.prod(action_shape))]
        self.model = nn.Sequential(*self.model)

    def forward(self, s, **kwargs):
        s = torch.tensor(s, device=self.device, dtype=torch.float)
        batch = s.shape[0]
        q = self.model(s.view(batch, -1))
        return q, None


def get_args():
    parser = argparse.ArgumentParser()
    parser.add_argument('--task', type=str, default='CartPole-v0')
    parser.add_argument('--seed', type=int, default=1626)
    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('--lr', type=float, default=3e-4)
    parser.add_argument('--gamma', type=float, default=0.9)
    parser.add_argument('--n-step', type=int, default=1)
    parser.add_argument('--epoch', type=int, default=100)
    parser.add_argument('--step-per-epoch', type=int, default=320)
    parser.add_argument('--collect-per-step', 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=8)
    parser.add_argument('--test-num', type=int, default=100)
    parser.add_argument('--logdir', type=str, default='log')
    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_dqn(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)
    train_envs = SubprocVectorEnv(
        [lambda: gym.make(args.task) for _ in range(args.training_num)],
        reset_after_done=True)
    # test_envs = gym.make(args.task)
    test_envs = SubprocVectorEnv(
        [lambda: gym.make(args.task) for _ in range(args.test_num)],
        reset_after_done=False)
    # 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.layer_num, args.state_shape, args.action_shape, args.device)
    net = net.to(args.device)
    optim = torch.optim.Adam(net.parameters(), lr=args.lr)
    policy = DQNPolicy(net, optim, args.gamma, args.n_step)
    # collector
    train_collector = Collector(
        policy, train_envs, ReplayBuffer(args.buffer_size))
    test_collector = Collector(policy, test_envs, stat_size=args.test_num)
    train_collector.collect(n_step=args.batch_size)
    # log
    writer = SummaryWriter(args.logdir)

    def stop_fn(x):
        return x >= env.spec.reward_threshold

    def train_fn(x):
        policy.sync_weight()
        policy.set_eps(args.eps_train)

    def test_fn(x):
        policy.set_eps(args.eps_test)

    # trainer
    result = offpolicy_trainer(
        policy, train_collector, test_collector, args.epoch,
        args.step_per_epoch, args.collect_per_step, args.test_num,
        args.batch_size, train_fn=train_fn, test_fn=test_fn,
        stop_fn=stop_fn, writer=writer)

    assert stop_fn(result['best_reward'])
    train_collector.close()
    test_collector.close()
    if __name__ == '__main__':
        pprint.pprint(result)
        # Let's watch its performance!
        env = gym.make(args.task)
        collector = Collector(policy, env)
        result = collector.collect(n_episode=1, render=1 / 35)
        print(f'Final reward: {result["rew"]}, length: {result["len"]}')
        collector.close()


if __name__ == '__main__':
    test_dqn(get_args())