Skip to content

Commit

Permalink
All the notebooks are working now.
Browse files Browse the repository at this point in the history
  • Loading branch information
@donlaiq
donlaiq committed Apr 21, 2024
1 parent 26d7e0b commit b035945
Show file tree
Hide file tree
Showing 13 changed files with 2,010 additions and 644 deletions.
29 changes: 19 additions & 10 deletions Chapter 1/Ch1_Introduction.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,10 @@
{
"cell_type": "markdown",
"metadata": {
"collapsed": true
"collapsed": true,
"jupyter": {
"outputs_hidden": true
}
},
"source": [
"# Deep Reinforcement Learning <em> in Action </em>\n",
Expand Down Expand Up @@ -87,14 +90,14 @@
},
{
"cell_type": "code",
"execution_count": 7,
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"5.54 s ± 432 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
"4.4 s ± 844 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
]
}
],
Expand All @@ -105,29 +108,35 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"The slowest run took 4.44 times longer than the fastest. This could mean that an intermediate result is being cached.\n",
"412 ns ± 319 ns per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
"319 ns ± 274 ns per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
]
}
],
"source": [
"%timeit fib_mem(35)\n",
"# We get 412 ns to run with n=35"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python [conda env:deeprl]",
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "conda-env-deeprl-py"
"name": "python3"
},
"language_info": {
"codemirror_mode": {
Expand All @@ -139,9 +148,9 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.5"
"version": "3.10.12"
}
},
"nbformat": 4,
"nbformat_minor": 2
"nbformat_minor": 4
}
250 changes: 220 additions & 30 deletions Chapter 10/Ch10_book.ipynb
View file

Large diffs are not rendered by default.

129 changes: 71 additions & 58 deletions Chapter 2/Ch2_book.ipynb
View file

Large diffs are not rendered by default.

377 changes: 295 additions & 82 deletions Chapter 3/Ch3_book.ipynb
View file

Large diffs are not rendered by default.

78 changes: 39 additions & 39 deletions Chapter 4/Ch4_book.ipynb
View file

Large diffs are not rendered by default.

137 changes: 116 additions & 21 deletions Chapter 5/Ch5_book.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -17,9 +17,21 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 1,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23\n",
" 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47\n",
" 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63]\n",
"8\n",
"[array([ 0, 1, 4, 9, 16, 25, 36, 49]), array([ 64, 81, 100, 121, 144, 169, 196, 225]), array([256, 289, 324, 361, 400, 441, 484, 529]), array([576, 625, 676, 729, 784, 841, 900, 961]), array([1024, 1089, 1156, 1225, 1296, 1369, 1444, 1521]), array([1600, 1681, 1764, 1849, 1936, 2025, 2116, 2209]), array([2304, 2401, 2500, 2601, 2704, 2809, 2916, 3025]), array([3136, 3249, 3364, 3481, 3600, 3721, 3844, 3969])]\n"
]
}
],
"source": [
"import multiprocessing as mp\n",
"import numpy as np\n",
Expand All @@ -42,9 +54,25 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 2,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"In process 0\n",
"In process 1\n",
"In process 2\n",
"In process 3\n",
"In process 4\n",
"In process 5\n",
"In process 6\n",
"In process 7\n",
"[array([ 0, 1, 4, 9, 16, 25, 36, 49]), array([ 64, 81, 100, 121, 144, 169, 196, 225]), array([256, 289, 324, 361, 400, 441, 484, 529]), array([576, 625, 676, 729, 784, 841, 900, 961]), array([1024, 1089, 1156, 1225, 1296, 1369, 1444, 1521]), array([1600, 1681, 1764, 1849, 1936, 2025, 2116, 2209]), array([2304, 2401, 2500, 2601, 2704, 2809, 2916, 3025]), array([3136, 3249, 3364, 3481, 3600, 3721, 3844, 3969])]\n"
]
}
],
"source": [
"def square(i, x, queue):\n",
" print(\"In process {}\".format(i,))\n",
Expand Down Expand Up @@ -79,9 +107,18 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 3,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/don/git/DeepReinforcementLearningInAction/venv/lib/python3.10/site-packages/gym/envs/registration.py:307: DeprecationWarning: The package name gym_minigrid has been deprecated in favor of minigrid. Please uninstall gym_minigrid and install minigrid with `pip install minigrid`. Future releases will be maintained under the new package name minigrid.\n",
" fn()\n"
]
}
],
"source": [
"import torch\n",
"from torch import nn\n",
Expand Down Expand Up @@ -118,7 +155,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -143,7 +180,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -161,7 +198,7 @@
" action = action_dist.sample() #E\n",
" logprob_ = policy.view(-1)[action]\n",
" logprobs.append(logprob_)\n",
" state_, _, done, info = worker_env.step(action.detach().numpy())\n",
" state_, _, done, _, info = worker_env.step(action.detach().numpy())\n",
" state = torch.from_numpy(state_).float()\n",
" if done: #F\n",
" reward = -10\n",
Expand All @@ -181,7 +218,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
Expand Down Expand Up @@ -215,7 +252,28 @@
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/don/git/DeepReinforcementLearningInAction/venv/lib/python3.10/site-packages/gym/utils/passive_env_checker.py:233: DeprecationWarning: `np.bool8` is a deprecated alias for `np.bool_`. (Deprecated NumPy 1.24)\n",
" if not isinstance(terminated, (bool, np.bool8)):\n",
"/home/don/git/DeepReinforcementLearningInAction/venv/lib/python3.10/site-packages/gym/utils/passive_env_checker.py:233: DeprecationWarning: `np.bool8` is a deprecated alias for `np.bool_`. (Deprecated NumPy 1.24)\n",
" if not isinstance(terminated, (bool, np.bool8)):\n",
"/home/don/git/DeepReinforcementLearningInAction/venv/lib/python3.10/site-packages/gym/utils/passive_env_checker.py:233: DeprecationWarning: `np.bool8` is a deprecated alias for `np.bool_`. (Deprecated NumPy 1.24)\n",
" if not isinstance(terminated, (bool, np.bool8)):\n",
"/home/don/git/DeepReinforcementLearningInAction/venv/lib/python3.10/site-packages/gym/utils/passive_env_checker.py:233: DeprecationWarning: `np.bool8` is a deprecated alias for `np.bool_`. (Deprecated NumPy 1.24)\n",
" if not isinstance(terminated, (bool, np.bool8)):\n",
"/home/don/git/DeepReinforcementLearningInAction/venv/lib/python3.10/site-packages/gym/utils/passive_env_checker.py:233: DeprecationWarning: `np.bool8` is a deprecated alias for `np.bool_`. (Deprecated NumPy 1.24)\n",
" if not isinstance(terminated, (bool, np.bool8)):\n",
"/home/don/git/DeepReinforcementLearningInAction/venv/lib/python3.10/site-packages/gym/utils/passive_env_checker.py:233: DeprecationWarning: `np.bool8` is a deprecated alias for `np.bool_`. (Deprecated NumPy 1.24)\n",
" if not isinstance(terminated, (bool, np.bool8)):\n",
"/home/don/git/DeepReinforcementLearningInAction/venv/lib/python3.10/site-packages/gym/utils/passive_env_checker.py:233: DeprecationWarning: `np.bool8` is a deprecated alias for `np.bool_`. (Deprecated NumPy 1.24)\n",
" if not isinstance(terminated, (bool, np.bool8)):\n"
]
}
],
"source": [
"MasterNode = ActorCritic() #A\n",
"MasterNode.share_memory() #B\n",
Expand Down Expand Up @@ -246,9 +304,28 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 9,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/don/git/DeepReinforcementLearningInAction/venv/lib/python3.10/site-packages/gym/envs/classic_control/cartpole.py:211: UserWarning: \u001b[33mWARN: You are calling render method without specifying any render mode. You can specify the render_mode at initialization, e.g. gym(\"CartPole-v1\", render_mode=\"rgb_array\")\u001b[0m\n",
" gym.logger.warn(\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Lost\n",
"Lost\n",
"Lost\n",
"Lost\n"
]
}
],
"source": [
"env = gym.make(\"CartPole-v1\")\n",
"env.reset()\n",
Expand All @@ -259,7 +336,7 @@
" logits,value = MasterNode(state)\n",
" action_dist = torch.distributions.Categorical(logits=logits)\n",
" action = action_dist.sample()\n",
" state2, reward, done, info = env.step(action.detach().numpy())\n",
" state2, reward, done, info, _ = env.step(action.detach().numpy())\n",
" if done:\n",
" print(\"Lost\")\n",
" env.reset()\n",
Expand All @@ -277,7 +354,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
Expand Down Expand Up @@ -318,9 +395,20 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 11,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"No bootstrapping\n",
"0.010000000000000009 1.99\n",
"With bootstrapping\n",
"0.9901 2.9701\n"
]
}
],
"source": [
"#Simulated rewards for 3 steps\n",
"r1 = [1,1,-1]\n",
Expand All @@ -342,13 +430,20 @@
"print(\"With bootstrapping\")\n",
"print(R1,R2)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python [conda env:deeprl]",
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "conda-env-deeprl-py"
"name": "python3"
},
"language_info": {
"codemirror_mode": {
Expand All @@ -360,9 +455,9 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.7"
"version": "3.10.12"
}
},
"nbformat": 4,
"nbformat_minor": 2
"nbformat_minor": 4
}
146 changes: 89 additions & 57 deletions Chapter 6/Ch6_book.ipynb
View file

Large diffs are not rendered by default.

Loading

0 comments on commit b035945

Please sign in to comment.