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

from tianshou.policy import TD3Policy
from tianshou.utils.net.common import Net
from tianshou.env import SubprocVectorEnv
from tianshou.exploration import GaussianNoise
from tianshou.trainer import offpolicy_trainer
from tianshou.data import Collector, ReplayBuffer
from tianshou.utils.net.continuous import Actor, Critic

from mujoco.register import reg


def get_args():
    parser = argparse.ArgumentParser()
    parser.add_argument('--task', type=str, default='PointMaze-v1')
    parser.add_argument('--seed', type=int, default=1626)
    parser.add_argument('--buffer-size', type=int, default=20000)
    parser.add_argument('--actor-lr', type=float, default=3e-5)
    parser.add_argument('--critic-lr', type=float, default=1e-4)
    parser.add_argument('--gamma', type=float, default=0.99)
    parser.add_argument('--tau', type=float, default=0.005)
    parser.add_argument('--exploration-noise', type=float, default=0.1)
    parser.add_argument('--policy-noise', type=float, default=0.2)
    parser.add_argument('--noise-clip', type=float, default=0.5)
    parser.add_argument('--update-actor-freq', type=int, default=2)
    parser.add_argument('--epoch', type=int, default=100)
    parser.add_argument('--step-per-epoch', type=int, default=2400)
    parser.add_argument('--collect-per-step', type=int, default=10)
    parser.add_argument('--batch-size', type=int, default=128)
    parser.add_argument('--hidden-sizes', type=int,
                        nargs='*', default=[128, 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')
    return parser.parse_args()


def test_td3(args=get_args()):
    reg()
    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]
    # train_envs = gym.make(args.task)
    train_envs = SubprocVectorEnv(
        [lambda: gym.make(args.task) for _ in range(args.training_num)])
    # 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 = Net(args.state_shape, hidden_sizes=args.hidden_sizes,
              device=args.device)
    actor = Actor(net, args.action_shape, max_action=args.max_action,
                  device=args.device).to(args.device)
    actor_optim = torch.optim.Adam(actor.parameters(), lr=args.actor_lr)
    net = Net(args.state_shape, args.action_shape,
              hidden_sizes=args.hidden_sizes, concat=True, device=args.device)
    critic1 = Critic(net, device=args.device).to(args.device)
    critic1_optim = torch.optim.Adam(critic1.parameters(), lr=args.critic_lr)
    net = Net(args.state_shape, args.action_shape,
              hidden_sizes=args.hidden_sizes, concat=True, device=args.device)
    critic2 = Critic(net, device=args.device).to(args.device)
    critic2_optim = torch.optim.Adam(critic2.parameters(), lr=args.critic_lr)
    policy = TD3Policy(
        actor, actor_optim, critic1, critic1_optim, critic2, critic2_optim,
        action_range=[env.action_space.low[0], env.action_space.high[0]],
        tau=args.tau, gamma=args.gamma,
        exploration_noise=GaussianNoise(sigma=args.exploration_noise),
        policy_noise=args.policy_noise,
        update_actor_freq=args.update_actor_freq,
        noise_clip=args.noise_clip,
        reward_normalization=True, ignore_done=True)
    # collector
    train_collector = Collector(
        policy, train_envs, ReplayBuffer(args.buffer_size))
    test_collector = Collector(policy, test_envs)
    # train_collector.collect(n_step=args.buffer_size)
    # log
    writer = SummaryWriter(args.logdir + '/' + 'td3')

    def stop_fn(mean_rewards):
        if env.spec.reward_threshold:
            return mean_rewards >= env.spec.reward_threshold
        else:
            return False

    # 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, stop_fn=stop_fn, writer=writer)
    assert stop_fn(result['best_reward'])
    if __name__ == '__main__':
        pprint.pprint(result)
        # Let's watch its performance!
        policy.eval()
        test_envs.seed(args.seed)
        test_collector.reset()
        result = test_collector.collect(n_episode=[1] * args.test_num,
                                        render=args.render)
        print(f'Final reward: {result["rew"]}, length: {result["len"]}')


if __name__ == '__main__':
    test_td3()