diff --git a/unit2/unit2.ipynb b/unit2/unit2.ipynb index 50bc773..0e06f72 100644 --- a/unit2/unit2.ipynb +++ b/unit2/unit2.ipynb @@ -207,7 +207,8 @@ "\n", "!pip install huggingface_hub\n", "!pip install pickle5\n", - "!pip install pyyaml==6.0 # avoid key error metadata" + "!pip install pyyaml==6.0 # avoid key error metadata\n", + "!pip install imageio imageio_ffmpeg" ], "metadata": { "id": "1Ac7wW_5ClJC" @@ -476,7 +477,7 @@ { "cell_type": "code", "source": [ - "initialize_q_table(state_space, action_space)" + "Qtable_frozenlake = initialize_q_table(state_space, action_space)" ], "metadata": { "id": "9YfvrqRt3jdR" @@ -566,9 +567,9 @@ "source": [ "def epsilon_greedy_policy(Qtable, state):\n", " # Randomly generate a number between 0 and 1\n", - " random_int = \n", - " # if random_int > greater than epsilon --> exploitation\n", - " if random_int > epsilon:\n", + " random_num = \n", + " # if random_num > greater than epsilon --> exploitation\n", + " if random_num > epsilon:\n", " # Take the action with the highest value given a state\n", " # np.argmax can be useful here\n", " action = \n", @@ -603,7 +604,7 @@ " if random_int > epsilon:\n", " # Take the action with the highest value given a state\n", " # np.argmax can be useful here\n", - " action = np.argmax(Q[state])\n", + " action = np.argmax(Qtable[state])\n", " # else --> exploration\n", " else:\n", " action = env.action_space.sample()\n", @@ -669,7 +670,7 @@ "source": [ "def greedy_policy(Qtable, state):\n", " # Exploitation: take the action with the highest state, action value\n", - " action = np.argmax(Q[state])\n", + " action = np.argmax(Qtable[state])\n", " \n", " return action" ], @@ -1030,9 +1031,8 @@ " api = HfApi()\n", " \n", " repo_url = api.create_repo(\n", - " name=repo_name,\n", + " repo_id=repo_id,\n", " token=token,\n", - " organization=organization,\n", " private=False,\n", " exist_ok=True,)\n", " \n", @@ -1284,10 +1284,10 @@ { "cell_type": "code", "source": [ - "push_to_hub(repo_id=\"ThomasSimonini/q-FrozenLake-v1-8x8-slippery\", \n", - " model=model,\n", - " env=env\n", - " )" + "repo_id = ", + "push_to_hub(repo_id=repo_id,\n", + " model=model,\n", + " env=env)" ], "metadata": { "id": "RpOTtSt83kPZ" @@ -1526,10 +1526,10 @@ { "cell_type": "code", "source": [ - "push_to_hub(repo_id = \"ThomasSimonini/q-Taxi-v3\", \n", - " model=model,\n", - " env=env\n", - " )" + "repo_id = \n", + "push_to_hub(repo_id=repo_id,\n", + " model=model,\n", + " env=env)" ], "metadata": { "id": "dhQtiQozhOn1" @@ -1709,7 +1709,7 @@ "* Try different hyperparameters by looking at what your classmates have done.\n", "* **Push your new trained model** on the Hub 🔥\n", "\n", - "Is moon landing too boring to you? Try to **change the environment**, why not using FrozenLake-v1 non slippery version? Check how they works [using the gym documentation](https://www.gymlibrary.ml/) and have fun 🎉." + "Are walking on ice and driving taxis too boring to you? Try to **change the environment**, why not using FrozenLake-v1 slippery version? Check how they work [using the gym documentation](https://www.gymlibrary.ml/) and have fun 🎉." ] }, { @@ -1778,4 +1778,4 @@ }, "nbformat": 4, "nbformat_minor": 0 -} \ No newline at end of file +}