import argparse
import os
import pprint

import gymnasium as gym
import numpy as np
import torch
from gymnasium.spaces import Box
from torch.utils.tensorboard import SummaryWriter

from tianshou.data import Collector, VectorReplayBuffer
from tianshou.env import DummyVectorEnv
from tianshou.policy import PGPolicy
from tianshou.policy.base import BasePolicy
from tianshou.trainer import OnpolicyTrainer
from tianshou.utils import TensorboardLogger
from tianshou.utils.net.common import Net
from tianshou.utils.space_info import SpaceInfo


def get_args() -> argparse.Namespace:
    parser = argparse.ArgumentParser()
    parser.add_argument("--task", type=str, default="CartPole-v1")
    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("--gamma", type=float, default=0.95)
    parser.add_argument("--epoch", type=int, default=10)
    parser.add_argument("--step-per-epoch", type=int, default=40000)
    parser.add_argument("--episode-per-collect", type=int, default=8)
    parser.add_argument("--repeat-per-collect", type=int, default=2)
    parser.add_argument("--batch-size", type=int, default=64)
    parser.add_argument("--hidden-sizes", type=int, nargs="*", default=[64, 64])
    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=0.0)
    parser.add_argument("--rew-norm", type=int, default=1)
    parser.add_argument(
        "--device",
        type=str,
        default="cuda" if torch.cuda.is_available() else "cpu",
    )
    return parser.parse_known_args()[0]


def test_pg(args: argparse.Namespace = get_args()) -> None:
    env = gym.make(args.task)
    space_info = SpaceInfo.from_env(env)
    args.state_shape = space_info.observation_info.obs_shape
    args.action_shape = space_info.action_info.action_shape
    if args.reward_threshold is None:
        default_reward_threshold = {"CartPole-v1": 195}
        args.reward_threshold = default_reward_threshold.get(
            args.task,
            env.spec.reward_threshold if env.spec else None,
        )
    # 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 = Net(
        state_shape=args.state_shape,
        action_shape=args.action_shape,
        hidden_sizes=args.hidden_sizes,
        device=args.device,
        softmax=True,
    ).to(args.device)
    optim = torch.optim.Adam(net.parameters(), lr=args.lr)
    dist_fn = torch.distributions.Categorical
    policy: PGPolicy = PGPolicy(
        actor=net,
        optim=optim,
        dist_fn=dist_fn,
        discount_factor=args.gamma,
        action_space=env.action_space,
        action_scaling=isinstance(env.action_space, Box),
        reward_normalization=args.rew_norm,
    )
    for m in net.modules():
        if isinstance(m, torch.nn.Linear):
            # orthogonal initialization
            torch.nn.init.orthogonal_(m.weight, gain=np.sqrt(2))
            torch.nn.init.zeros_(m.bias)
    # 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, "pg")
    writer = SummaryWriter(log_path)
    logger = TensorboardLogger(writer)

    def save_best_fn(policy: BasePolicy) -> None:
        torch.save(policy.state_dict(), os.path.join(log_path, "policy.pth"))

    def stop_fn(mean_rewards: float) -> bool:
        return mean_rewards >= args.reward_threshold

    # trainer
    result = OnpolicyTrainer(
        policy=policy,
        train_collector=train_collector,
        test_collector=test_collector,
        max_epoch=args.epoch,
        step_per_epoch=args.step_per_epoch,
        repeat_per_collect=args.repeat_per_collect,
        episode_per_test=args.test_num,
        batch_size=args.batch_size,
        episode_per_collect=args.episode_per_collect,
        stop_fn=stop_fn,
        save_best_fn=save_best_fn,
        logger=logger,
    ).run()
    assert stop_fn(result.best_reward)

    if __name__ == "__main__":
        pprint.pprint(result)
        # Let's watch its performance!
        env = gym.make(args.task)
        collector = Collector(policy, env)
        collector.reset()
        collector_stats = collector.collect(n_episode=1, render=args.render, is_eval=True)
        print(collector_stats)


if __name__ == "__main__":
    test_pg()