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

from tianshou.policy import DQNPolicy
from tianshou.utils import TensorboardLogger
from tianshou.env import DummyVectorEnv
from tianshou.trainer import offpolicy_trainer
from tianshou.utils.net.common import Recurrent
from tianshou.data import Collector, VectorReplayBuffer


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('--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('--stack-num', type=int, default=4)
    parser.add_argument('--lr', type=float, default=1e-3)
    parser.add_argument('--gamma', type=float, default=0.95)
    parser.add_argument('--n-step', type=int, default=3)
    parser.add_argument('--target-update-freq', type=int, default=320)
    parser.add_argument('--epoch', type=int, default=5)
    parser.add_argument('--step-per-epoch', type=int, default=20000)
    parser.add_argument('--update-per-step', type=float, default=1 / 16)
    parser.add_argument('--step-per-collect', type=int, default=16)
    parser.add_argument('--batch-size', type=int, default=128)
    parser.add_argument('--layer-num', type=int, default=2)
    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')
    args = parser.parse_known_args()[0]
    return args


def test_drqn(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)
    # you can also use tianshou.env.SubprocVectorEnv
    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 = Recurrent(args.layer_num, args.state_shape,
                    args.action_shape, args.device).to(args.device)
    optim = torch.optim.Adam(net.parameters(), lr=args.lr)
    policy = DQNPolicy(
        net, optim, args.gamma, args.n_step,
        target_update_freq=args.target_update_freq)
    # collector
    buffer = VectorReplayBuffer(
        args.buffer_size, buffer_num=len(train_envs),
        stack_num=args.stack_num, ignore_obs_next=True)
    train_collector = Collector(policy, train_envs, buffer, exploration_noise=True)
    # the stack_num is for RNN training: sample framestack obs
    test_collector = Collector(policy, test_envs, exploration_noise=True)
    # policy.set_eps(1)
    train_collector.collect(n_step=args.batch_size * args.training_num)
    # log
    log_path = os.path.join(args.logdir, args.task, 'drqn')
    writer = SummaryWriter(log_path)
    logger = TensorboardLogger(writer)

    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

    def train_fn(epoch, env_step):
        policy.set_eps(args.eps_train)

    def test_fn(epoch, env_step):
        policy.set_eps(args.eps_test)

    # 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, update_per_step=args.update_per_step,
        train_fn=train_fn, test_fn=test_fn, stop_fn=stop_fn,
        save_fn=save_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()}")


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