add RL Notebook

%% Cell type:code id: tags:

``` python

import gymnasium as gym

import matplotlib.pyplot as plt

from IPython.display import clear_output

env = gym.make("CliffWalking-v0", render_mode="rgb_array")

env.action_space.seed(42)

observation, info = env.reset(seed=42)

for _ in range(100):

    observation, reward, terminated, truncated, info = env.step(env.action_space.sample())

    if terminated:

        observation, info = env.reset(return_info=True)

    clear_output(wait=True)

    plt.imshow(env.render())

    plt.show()

```

%% Cell type:code id: tags:

``` python

from cliff import CliffAgent

from tqdm import tqdm

learning_rate = 0.01

n_episodes = 100_0

start_epsilon = 1.0

final_epsilon = 0.0

discount_factor = 0.95

max_steps_per_epoch = 100_0

show_env = False

# update_algorithm either "q_learning" or "sarsa"

agent = CliffAgent(

    show_env=show_env,

    learning_rate=learning_rate,

    initial_epsilon=start_epsilon,

    final_epsilon=final_epsilon,

    discount_factor=discount_factor,

    max_steps_per_epoch=max_steps_per_epoch,

    update_algorithm="q_learning"

    # update_algorithm="sarsa"

)

# agent.env = gym.wrappers.RecordEpisodeStatistics(agent.env)

for episode in tqdm(range(n_episodes)):

    agent.perform_epoch(eps_decay_over_n_epochs=n_episodes)

agent.vis_results(n_episodes)

```