diff --git a/M2/Reinforcement Learning/Lab 2 - Maze Game as a Markov Decision Process Part 1.ipynb b/M2/Reinforcement Learning/Lab 2 - Maze Game as a Markov Decision Process Part 1.ipynb index cc0c383..4152698 100644 --- a/M2/Reinforcement Learning/Lab 2 - Maze Game as a Markov Decision Process Part 1.ipynb +++ b/M2/Reinforcement Learning/Lab 2 - Maze Game as a Markov Decision Process Part 1.ipynb @@ -31,7 +31,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 1, "id": "100d1e0d", "metadata": {}, "outputs": [], @@ -100,7 +100,7 @@ }, { "cell_type": "code", - "execution_count": 74, + "execution_count": 2, "id": "f91cda05", "metadata": {}, "outputs": [], @@ -128,7 +128,7 @@ }, { "cell_type": "code", - "execution_count": 75, + "execution_count": 3, "id": "564cb757-eefe-4be6-9b6f-bb77ace42a97", "metadata": {}, "outputs": [ @@ -150,7 +150,7 @@ }, { "cell_type": "code", - "execution_count": 76, + "execution_count": 4, "id": "26c821d3-2362-4b60-8c77-3d09296d130d", "metadata": {}, "outputs": [ @@ -200,7 +200,7 @@ }, { "cell_type": "code", - "execution_count": 77, + "execution_count": 5, "id": "7116044b-c134-43de-9f30-01ab62325300", "metadata": {}, "outputs": [], @@ -231,7 +231,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 6, "id": "a1258de4", "metadata": {}, "outputs": [ @@ -292,7 +292,7 @@ }, { "cell_type": "code", - "execution_count": 79, + "execution_count": 7, "id": "68744dd6-7278-4c20-8b82-34212685352f", "metadata": {}, "outputs": [ @@ -366,7 +366,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 8, "id": "fc61ceef-217c-47f4-8eba-0353369210db", "metadata": {}, "outputs": [ @@ -476,7 +476,7 @@ }, { "cell_type": "code", - "execution_count": 81, + "execution_count": 9, "id": "f7f0b8e4-1f48-4d03-9e5f-a47e59c3e827", "metadata": {}, "outputs": [], @@ -488,7 +488,7 @@ }, { "cell_type": "code", - "execution_count": 82, + "execution_count": 10, "id": "3773781c-a0cd-48db-967b-d4b432d17046", "metadata": {}, "outputs": [ @@ -518,7 +518,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 11, "id": "4b06da5e-bc63-48e5-a336-37bce952443d", "metadata": {}, "outputs": [], @@ -597,7 +597,7 @@ }, { "cell_type": "code", - "execution_count": 84, + "execution_count": 12, "id": "610253e7-f3f7-4a30-be3e-2ec5a1e2ed04", "metadata": {}, "outputs": [], @@ -628,7 +628,7 @@ }, { "cell_type": "code", - "execution_count": 85, + "execution_count": 13, "id": "7a51f242-fe4e-4e74-8a1f-a8df32b194b8", "metadata": {}, "outputs": [], @@ -656,7 +656,7 @@ }, { "cell_type": "code", - "execution_count": 86, + "execution_count": 14, "id": "49d54d1f-dc29-45b6-ad31-ad0e848f920d", "metadata": {}, "outputs": [], @@ -701,7 +701,7 @@ }, { "cell_type": "code", - "execution_count": 87, + "execution_count": 15, "id": "b9b7495a-c233-425c-99c0-5bddaf6c3225", "metadata": {}, "outputs": [], @@ -727,7 +727,7 @@ }, { "cell_type": "code", - "execution_count": 88, + "execution_count": 16, "id": "eca4c571-39c7-468b-af86-0bab9489415e", "metadata": {}, "outputs": [], @@ -758,7 +758,7 @@ }, { "cell_type": "code", - "execution_count": 89, + "execution_count": 17, "id": "2d03276b-e206-4d1f-9024-f6948ca61523", "metadata": {}, "outputs": [], @@ -821,7 +821,7 @@ }, { "cell_type": "code", - "execution_count": 90, + "execution_count": 18, "id": "341fe630-8f87-4773-84ad-92d3516e53e2", "metadata": {}, "outputs": [ @@ -968,7 +968,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 19, "id": "2fffe0b7", "metadata": {}, "outputs": [], @@ -1037,7 +1037,7 @@ }, { "cell_type": "code", - "execution_count": 92, + "execution_count": 20, "id": "b4a44e38", "metadata": {}, "outputs": [ @@ -1066,7 +1066,7 @@ }, { "cell_type": "code", - "execution_count": 93, + "execution_count": 21, "id": "c5f559b2-452a-477c-a1fa-258b40805670", "metadata": {}, "outputs": [ @@ -1110,7 +1110,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 22, "id": "4c428327", "metadata": {}, "outputs": [ @@ -1184,7 +1184,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 23, "id": "c1ab67f0-bd5e-4ffe-b655-aec030401b78", "metadata": {}, "outputs": [], @@ -1269,7 +1269,7 @@ }, { "cell_type": "code", - "execution_count": 96, + "execution_count": 24, "id": "d452681c-c89c-41cc-95dc-df75993b0391", "metadata": {}, "outputs": [ @@ -1298,7 +1298,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 25, "id": "929707e6-3022-4d86-96cc-12f251f890a9", "metadata": {}, "outputs": [ @@ -1324,7 +1324,7 @@ } ], "source": [ - "my_policy = np.ndarray(\n", + "my_policy = np.array(\n", " [\n", " A_RIGHT,\n", " A_RIGHT,\n", @@ -1403,7 +1403,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.12" + "version": "3.13.9" } }, "nbformat": 4, diff --git a/M2/Reinforcement Learning/Lab 2 - Second maze.ipynb b/M2/Reinforcement Learning/Lab 2 - Second maze.ipynb index 4738b76..fb592fd 100644 --- a/M2/Reinforcement Learning/Lab 2 - Second maze.ipynb +++ b/M2/Reinforcement Learning/Lab 2 - Second maze.ipynb @@ -14,7 +14,7 @@ }, { "cell_type": "code", - "execution_count": 535, + "execution_count": 24, "id": "100d1e0d", "metadata": {}, "outputs": [], @@ -49,7 +49,7 @@ }, { "cell_type": "code", - "execution_count": 536, + "execution_count": 25, "id": "f91cda05", "metadata": {}, "outputs": [], @@ -72,7 +72,7 @@ }, { "cell_type": "code", - "execution_count": 537, + "execution_count": 26, "id": "564cb757-eefe-4be6-9b6f-bb77ace42a97", "metadata": {}, "outputs": [], @@ -93,7 +93,7 @@ }, { "cell_type": "code", - "execution_count": 538, + "execution_count": 27, "id": "7116044b-c134-43de-9f30-01ab62325300", "metadata": {}, "outputs": [], @@ -116,7 +116,7 @@ }, { "cell_type": "code", - "execution_count": 539, + "execution_count": 28, "id": "a1258de4", "metadata": {}, "outputs": [ @@ -170,7 +170,7 @@ }, { "cell_type": "code", - "execution_count": 540, + "execution_count": 29, "id": "fc61ceef-217c-47f4-8eba-0353369210db", "metadata": {}, "outputs": [ @@ -250,7 +250,7 @@ }, { "cell_type": "code", - "execution_count": 541, + "execution_count": 30, "id": "f7f0b8e4-1f48-4d03-9e5f-a47e59c3e827", "metadata": {}, "outputs": [], @@ -262,7 +262,7 @@ }, { "cell_type": "code", - "execution_count": 542, + "execution_count": 31, "id": "4b06da5e-bc63-48e5-a336-37bce952443d", "metadata": {}, "outputs": [], @@ -330,7 +330,7 @@ }, { "cell_type": "code", - "execution_count": 543, + "execution_count": 32, "id": "610253e7-f3f7-4a30-be3e-2ec5a1e2ed04", "metadata": {}, "outputs": [], @@ -341,7 +341,7 @@ }, { "cell_type": "code", - "execution_count": 544, + "execution_count": 33, "id": "7a51f242-fe4e-4e74-8a1f-a8df32b194b8", "metadata": {}, "outputs": [], @@ -353,7 +353,7 @@ }, { "cell_type": "code", - "execution_count": 545, + "execution_count": 34, "id": "49d54d1f-dc29-45b6-ad31-ad0e848f920d", "metadata": {}, "outputs": [], @@ -366,7 +366,7 @@ }, { "cell_type": "code", - "execution_count": 546, + "execution_count": 35, "id": "b9b7495a-c233-425c-99c0-5bddaf6c3225", "metadata": {}, "outputs": [], @@ -382,7 +382,7 @@ }, { "cell_type": "code", - "execution_count": 547, + "execution_count": 36, "id": "eca4c571-39c7-468b-af86-0bab9489415e", "metadata": {}, "outputs": [], @@ -397,7 +397,7 @@ }, { "cell_type": "code", - "execution_count": 548, + "execution_count": 37, "id": "2d03276b-e206-4d1f-9024-f6948ca61523", "metadata": {}, "outputs": [], @@ -445,7 +445,7 @@ }, { "cell_type": "code", - "execution_count": 549, + "execution_count": 38, "id": "341fe630-8f87-4773-84ad-92d3516e53e2", "metadata": {}, "outputs": [ @@ -492,7 +492,7 @@ }, { "cell_type": "code", - "execution_count": 550, + "execution_count": 39, "id": "2fffe0b7", "metadata": {}, "outputs": [], @@ -543,7 +543,7 @@ }, { "cell_type": "code", - "execution_count": 551, + "execution_count": 40, "id": "4c428327", "metadata": {}, "outputs": [], @@ -595,7 +595,7 @@ }, { "cell_type": "code", - "execution_count": 552, + "execution_count": null, "id": "c1ab67f0-bd5e-4ffe-b655-aec030401b78", "metadata": {}, "outputs": [], @@ -665,7 +665,7 @@ " ax.set_yticks(np.arange(-0.5, n_rows, 1))\n", " ax.set_xticklabels([])\n", " ax.set_yticklabels([])\n", - " ax.grid(True)\n", + " ax.grid(visible=True)\n", " ax.set_title(title)\n", " plt.show()" ] @@ -680,7 +680,7 @@ }, { "cell_type": "code", - "execution_count": 553, + "execution_count": 42, "id": "ceb5dfe2", "metadata": {}, "outputs": [ @@ -702,7 +702,7 @@ }, { "cell_type": "code", - "execution_count": 554, + "execution_count": 43, "id": "8f3e2ac2", "metadata": {}, "outputs": [ @@ -729,7 +729,7 @@ }, { "cell_type": "code", - "execution_count": 558, + "execution_count": 44, "id": "cf45291e", "metadata": {}, "outputs": [ @@ -761,7 +761,7 @@ }, { "cell_type": "code", - "execution_count": 557, + "execution_count": 45, "id": "5a82a3b7", "metadata": {}, "outputs": [ @@ -787,7 +787,7 @@ } ], "source": [ - "my_policy = [\n", + "my_policy = np.array([\n", " A_DOWN,\n", " A_DOWN,\n", " A_LEFT,\n", @@ -850,7 +850,7 @@ " A_UP,\n", " A_DOWN,\n", " A_LEFT,\n", - "]\n", + "])\n", "\n", "V_my_policy = policy_evaluation(policy=my_policy, P=P, R=R, gamma=gamma)\n", "\n",