pip install -r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit2/requirements-unit2.txt

sudo apt-get update
sudo apt-get install -y python3-opengl
apt install ffmpeg xvfb
pip3 install pyvirtualdisplay

import os

os.kill(os.getpid(), 9)

# Virtual display
from pyvirtualdisplay import Display

virtual_display = Display(visible=0, size=(1400, 900))
virtual_display.start()

import numpy as np
import gymnasium as gym
import random
import imageio
import os
import tqdm

import pickle5 as pickle
from tqdm.notebook import tqdm

# Create the FrozenLake-v1 environment using 4x4 map and non-slippery version and render_mode="rgb_array"
env = gym.make()  # TODO use the correct parameters

env = gym.make("FrozenLake-v1", map_name="4x4", is_slippery=False, render_mode="rgb_array")

desc=["SFFF", "FHFH", "FFFH", "HFFG"]
gym.make('FrozenLake-v1', desc=desc, is_slippery=True)

# We create our environment with gym.make("<name_of_the_environment>")- `is_slippery=False`: The agent always moves in the intended direction due to the non-slippery nature of the frozen lake (deterministic).
print("_____OBSERVATION SPACE_____ \n")
print("Observation Space", env.observation_space)
print("Sample observation", env.observation_space.sample())  # Get a random observation

print("\n _____ACTION SPACE_____ \n")
print("Action Space Shape", env.action_space.n)
print("Action Space Sample", env.action_space.sample())  # Take a random action

state_space =
print("There are ", state_space, " possible states")

action_space =
print("There are ", action_space, " possible actions")

# Let's create our Qtable of size (state_space, action_space) and initialized each values at 0 using np.zeros. np.zeros needs a tuple (a,b)
def initialize_q_table(state_space, action_space):
  Qtable =
  return Qtable

Qtable_frozenlake = initialize_q_table(state_space, action_space)

state_space = env.observation_space.n
print("There are ", state_space, " possible states")

action_space = env.action_space.n
print("There are ", action_space, " possible actions")

# Let's create our Qtable of size (state_space, action_space) and initialized each values at 0 using np.zeros
def initialize_q_table(state_space, action_space):
    Qtable = np.zeros((state_space, action_space))
    return Qtable

Qtable_frozenlake = initialize_q_table(state_space, action_space)

def greedy_policy(Qtable, state):
  # Exploitation: take the action with the highest state, action value
  action =

  return action

def greedy_policy(Qtable, state):
    # Exploitation: take the action with the highest state, action value
    action = np.argmax(Qtable[state][:])

    return action

def epsilon_greedy_policy(Qtable, state, epsilon):
  # Randomly generate a number between 0 and 1
  random_num =
  # if random_num > greater than epsilon --> exploitation
  if random_num > epsilon:
    # Take the action with the highest value given a state
    # np.argmax can be useful here
    action =
  # else --> exploration
  else:
    action = # Take a random action

  return action

def epsilon_greedy_policy(Qtable, state, epsilon):
    # Randomly generate a number between 0 and 1
    random_num = random.uniform(0, 1)
    # if random_num > greater than epsilon --> exploitation
    if random_num > epsilon:
        # Take the action with the highest value given a state
        # np.argmax can be useful here
        action = greedy_policy(Qtable, state)
    # else --> exploration
    else:
        action = env.action_space.sample()

    return action

# Training parameters
n_training_episodes = 10000  # Total training episodes
learning_rate = 0.7  # Learning rate

# Evaluation parameters
n_eval_episodes = 100  # Total number of test episodes

# Environment parameters
env_id = "FrozenLake-v1"  # Name of the environment
max_steps = 99  # Max steps per episode
gamma = 0.95  # Discounting rate
eval_seed = []  # The evaluation seed of the environment

# Exploration parameters
max_epsilon = 1.0  # Exploration probability at start
min_epsilon = 0.05  # Minimum exploration probability
decay_rate = 0.0005  # Exponential decay rate for exploration prob

For episode in the total of training episodes:

Reduce epsilon (since we need less and less exploration)
Reset the environment

  For step in max timesteps:
    Choose the action At using epsilon greedy policy
    Take the action (a) and observe the outcome state(s') and reward (r)
    Update the Q-value Q(s,a) using Bellman equation Q(s,a) + lr [R(s,a) + gamma * max Q(s',a') - Q(s,a)]
    If done, finish the episode
    Our next state is the new state

def train(n_training_episodes, min_epsilon, max_epsilon, decay_rate, env, max_steps, Qtable):
  for episode in tqdm(range(n_training_episodes)):
    # Reduce epsilon (because we need less and less exploration)
    epsilon = min_epsilon + (max_epsilon - min_epsilon)*np.exp(-decay_rate*episode)
    # Reset the environment
    state, info = env.reset()
    step = 0
    terminated = False
    truncated = False

    # repeat
    for step in range(max_steps):
      # Choose the action At using epsilon greedy policy
      action =

      # Take action At and observe Rt+1 and St+1
      # Take the action (a) and observe the outcome state(s') and reward (r)
      new_state, reward, terminated, truncated, info =

      # Update Q(s,a):= Q(s,a) + lr [R(s,a) + gamma * max Q(s',a') - Q(s,a)]
      Qtable[state][action] =

      # If terminated or truncated finish the episode
      if terminated or truncated:
        break

      # Our next state is the new state
      state = new_state
  return Qtable

def train(n_training_episodes, min_epsilon, max_epsilon, decay_rate, env, max_steps, Qtable):
    for episode in tqdm(range(n_training_episodes)):
        # Reduce epsilon (because we need less and less exploration)
        epsilon = min_epsilon + (max_epsilon - min_epsilon) * np.exp(-decay_rate * episode)
        # Reset the environment
        state, info = env.reset()
        step = 0
        terminated = False
        truncated = False

        # repeat
        for step in range(max_steps):
            # Choose the action At using epsilon greedy policy
            action = epsilon_greedy_policy(Qtable, state, epsilon)

            # Take action At and observe Rt+1 and St+1
            # Take the action (a) and observe the outcome state(s') and reward (r)
            new_state, reward, terminated, truncated, info = env.step(action)

            # Update Q(s,a):= Q(s,a) + lr [R(s,a) + gamma * max Q(s',a') - Q(s,a)]
            Qtable[state][action] = Qtable[state][action] + learning_rate * (
                reward + gamma * np.max(Qtable[new_state]) - Qtable[state][action]
            )

            # If terminated or truncated finish the episode
            if terminated or truncated:
                break

            # Our next state is the new state
            state = new_state
    return Qtable

Qtable_frozenlake = train(n_training_episodes, min_epsilon, max_epsilon, decay_rate, env, max_steps, Qtable_frozenlake)

Qtable_frozenlake

def evaluate_agent(env, max_steps, n_eval_episodes, Q, seed):
    """
    Evaluate the agent for ``n_eval_episodes`` episodes and returns average reward and std of reward.
    :param env: The evaluation environment
    :param n_eval_episodes: Number of episode to evaluate the agent
    :param Q: The Q-table
    :param seed: The evaluation seed array (for taxi-v3)
    """
    episode_rewards = []
    for episode in tqdm(range(n_eval_episodes)):
        if seed:
            state, info = env.reset(seed=seed[episode])
        else:
            state, info = env.reset()
        step = 0
        truncated = False
        terminated = False
        total_rewards_ep = 0

        for step in range(max_steps):
            # Take the action (index) that have the maximum expected future reward given that state
            action = greedy_policy(Q, state)
            new_state, reward, terminated, truncated, info = env.step(action)
            total_rewards_ep += reward

            if terminated or truncated:
                break
            state = new_state
        episode_rewards.append(total_rewards_ep)
    mean_reward = np.mean(episode_rewards)
    std_reward = np.std(episode_rewards)

    return mean_reward, std_reward

# Evaluate our Agent
mean_reward, std_reward = evaluate_agent(env, max_steps, n_eval_episodes, Qtable_frozenlake, eval_seed)
print(f"Mean_reward={mean_reward:.2f} +/- {std_reward:.2f}")

from huggingface_hub import HfApi, snapshot_download
from huggingface_hub.repocard import metadata_eval_result, metadata_save

from pathlib import Path
import datetime
import json

def record_video(env, Qtable, out_directory, fps=1):
    """
    Generate a replay video of the agent
    :param env
    :param Qtable: Qtable of our agent
    :param out_directory
    :param fps: how many frame per seconds (with taxi-v3 and frozenlake-v1 we use 1)
    """
    images = []
    terminated = False
    truncated = False
    state, info = env.reset(seed=random.randint(0, 500))
    img = env.render()
    images.append(img)
    while not terminated or truncated:
        # Take the action (index) that have the maximum expected future reward given that state
        action = np.argmax(Qtable[state][:])
        state, reward, terminated, truncated, info = env.step(
            action
        )  # We directly put next_state = state for recording logic
        img = env.render()
        images.append(img)
    imageio.mimsave(out_directory, [np.array(img) for i, img in enumerate(images)], fps=fps)

def push_to_hub(repo_id, model, env, video_fps=1, local_repo_path="hub"):
    """
    Evaluate, Generate a video and Upload a model to Hugging Face Hub.
    This method does the complete pipeline:
    - It evaluates the model
    - It generates the model card
    - It generates a replay video of the agent
    - It pushes everything to the Hub

    :param repo_id: repo_id: id of the model repository from the Hugging Face Hub
    :param env
    :param video_fps: how many frame per seconds to record our video replay
    (with taxi-v3 and frozenlake-v1 we use 1)
    :param local_repo_path: where the local repository is
    """
    _, repo_name = repo_id.split("/")

    eval_env = env
    api = HfApi()

    # Step 1: Create the repo
    repo_url = api.create_repo(
        repo_id=repo_id,
        exist_ok=True,
    )

    # Step 2: Download files
    repo_local_path = Path(snapshot_download(repo_id=repo_id))

    # Step 3: Save the model
    if env.spec.kwargs.get("map_name"):
        model["map_name"] = env.spec.kwargs.get("map_name")
        if env.spec.kwargs.get("is_slippery", "") == False:
            model["slippery"] = False

    # Pickle the model
    with open((repo_local_path) / "q-learning.pkl", "wb") as f:
        pickle.dump(model, f)

    # Step 4: Evaluate the model and build JSON with evaluation metrics
    mean_reward, std_reward = evaluate_agent(
        eval_env, model["max_steps"], model["n_eval_episodes"], model["qtable"], model["eval_seed"]
    )

    evaluate_data = {
        "env_id": model["env_id"],
        "mean_reward": mean_reward,
        "n_eval_episodes": model["n_eval_episodes"],
        "eval_datetime": datetime.datetime.now().isoformat(),
    }

    # Write a JSON file called "results.json" that will contain the
    # evaluation results
    with open(repo_local_path / "results.json", "w") as outfile:
        json.dump(evaluate_data, outfile)

    # Step 5: Create the model card
    env_name = model["env_id"]
    if env.spec.kwargs.get("map_name"):
        env_name += "-" + env.spec.kwargs.get("map_name")

    if env.spec.kwargs.get("is_slippery", "") == False:
        env_name += "-" + "no_slippery"

    metadata = {}
    metadata["tags"] = [env_name, "q-learning", "reinforcement-learning", "custom-implementation"]

    # Add metrics
    eval = metadata_eval_result(
        model_pretty_name=repo_name,
        task_pretty_name="reinforcement-learning",
        task_id="reinforcement-learning",
        metrics_pretty_name="mean_reward",
        metrics_id="mean_reward",
        metrics_value=f"{mean_reward:.2f} +/- {std_reward:.2f}",
        dataset_pretty_name=env_name,
        dataset_id=env_name,
    )

    # Merges both dictionaries
    metadata = {**metadata, **eval}

    model_card = f"""
  # **Q-Learning** Agent playing1 **{env_id}**
  This is a trained model of a **Q-Learning** agent playing **{env_id}** .

  ## Usage

  model = load_from_hub(repo_id="{repo_id}", filename="q-learning.pkl")

  # Don't forget to check if you need to add additional attributes (is_slippery=False etc)
  env = gym.make(model["env_id"])
  """

    evaluate_agent(env, model["max_steps"], model["n_eval_episodes"], model["qtable"], model["eval_seed"])

    readme_path = repo_local_path / "README.md"
    readme = ""
    print(readme_path.exists())
    if readme_path.exists():
        with readme_path.open("r", encoding="utf8") as f:
            readme = f.read()
    else:
        readme = model_card

    with readme_path.open("w", encoding="utf-8") as f:
        f.write(readme)

    # Save our metrics to Readme metadata
    metadata_save(readme_path, metadata)

    # Step 6: Record a video
    video_path = repo_local_path / "replay.mp4"
    record_video(env, model["qtable"], video_path, video_fps)

    # Step 7. Push everything to the Hub
    api.upload_folder(
        repo_id=repo_id,
        folder_path=repo_local_path,
        path_in_repo=".",
    )

    print("Your model is pushed to the Hub. You can view your model here: ", repo_url)

from huggingface_hub import notebook_login

notebook_login()

model = {
    "env_id": env_id,
    "max_steps": max_steps,
    "n_training_episodes": n_training_episodes,
    "n_eval_episodes": n_eval_episodes,
    "eval_seed": eval_seed,
    "learning_rate": learning_rate,
    "gamma": gamma,
    "max_epsilon": max_epsilon,
    "min_epsilon": min_epsilon,
    "decay_rate": decay_rate,
    "qtable": Qtable_frozenlake,
}

model

username = ""  # FILL THIS
repo_name = "q-FrozenLake-v1-4x4-noSlippery"
push_to_hub(repo_id=f"{username}/{repo_name}", model=model, env=env)

env = gym.make("Taxi-v3", render_mode="rgb_array")

state_space = env.observation_space.n
print("There are ", state_space, " possible states")

action_space = env.action_space.n
print("There are ", action_space, " possible actions")

# Create our Q table with state_size rows and action_size columns (500x6)
Qtable_taxi = initialize_q_table(state_space, action_space)
print(Qtable_taxi)
print("Q-table shape: ", Qtable_taxi.shape)

# Training parameters
n_training_episodes = 25000  # Total training episodes
learning_rate = 0.7  # Learning rate

# Evaluation parameters
n_eval_episodes = 100  # Total number of test episodes

# DO NOT MODIFY EVAL_SEED
eval_seed = [
    16,
    54,
    165,
    177,
    191,
    191,
    120,
    80,
    149,
    178,
    48,
    38,
    6,
    125,
    174,
    73,
    50,
    172,
    100,
    148,
    146,
    6,
    25,
    40,
    68,
    148,
    49,
    167,
    9,
    97,
    164,
    176,
    61,
    7,
    54,
    55,
    161,
    131,
    184,
    51,
    170,
    12,
    120,
    113,
    95,
    126,
    51,
    98,
    36,
    135,
    54,
    82,
    45,
    95,
    89,
    59,
    95,
    124,
    9,
    113,
    58,
    85,
    51,
    134,
    121,
    169,
    105,
    21,
    30,
    11,
    50,
    65,
    12,
    43,
    82,
    145,
    152,
    97,
    106,
    55,
    31,
    85,
    38,
    112,
    102,
    168,
    123,
    97,
    21,
    83,
    158,
    26,
    80,
    63,
    5,
    81,
    32,
    11,
    28,
    148,
]  # Evaluation seed, this ensures that all classmates agents are trained on the same taxi starting position
# Each seed has a specific starting state

# Environment parameters
env_id = "Taxi-v3"  # Name of the environment
max_steps = 99  # Max steps per episode
gamma = 0.95  # Discounting rate

# Exploration parameters
max_epsilon = 1.0  # Exploration probability at start
min_epsilon = 0.05  # Minimum exploration probability
decay_rate = 0.005  # Exponential decay rate for exploration prob

Qtable_taxi = train(n_training_episodes, min_epsilon, max_epsilon, decay_rate, env, max_steps, Qtable_taxi)
Qtable_taxi

model = {
    "env_id": env_id,
    "max_steps": max_steps,
    "n_training_episodes": n_training_episodes,
    "n_eval_episodes": n_eval_episodes,
    "eval_seed": eval_seed,
    "learning_rate": learning_rate,
    "gamma": gamma,
    "max_epsilon": max_epsilon,
    "min_epsilon": min_epsilon,
    "decay_rate": decay_rate,
    "qtable": Qtable_taxi,
}

username = ""  # FILL THIS
repo_name = ""  # FILL THIS
push_to_hub(repo_id=f"{username}/{repo_name}", model=model, env=env)

from urllib.error import HTTPError

from huggingface_hub import hf_hub_download


def load_from_hub(repo_id: str, filename: str) -> str:
    """
    Download a model from Hugging Face Hub.
    :param repo_id: id of the model repository from the Hugging Face Hub
    :param filename: name of the model zip file from the repository
    """
    # Get the model from the Hub, download and cache the model on your local disk
    pickle_model = hf_hub_download(repo_id=repo_id, filename=filename)

    with open(pickle_model, "rb") as f:
        downloaded_model_file = pickle.load(f)

    return downloaded_model_file

model = load_from_hub(repo_id="ThomasSimonini/q-Taxi-v3", filename="q-learning.pkl")  # Try to use another model

print(model)
env = gym.make(model["env_id"])

evaluate_agent(env, model["max_steps"], model["n_eval_episodes"], model["qtable"], model["eval_seed"])

model = load_from_hub(
    repo_id="ThomasSimonini/q-FrozenLake-v1-no-slippery", filename="q-learning.pkl"
)  # Try to use another model

env = gym.make(model["env_id"], is_slippery=False)

evaluate_agent(env, model["max_steps"], model["n_eval_episodes"], model["qtable"], model["eval_seed"])