├── .gitignore ├── Jupyter └── RL_shower.ipynb ├── LICENSE └── README.md /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | build/ 12 | develop-eggs/ 13 | dist/ 14 | downloads/ 15 | eggs/ 16 | .eggs/ 17 | lib/ 18 | lib64/ 19 | parts/ 20 | sdist/ 21 | var/ 22 | wheels/ 23 | pip-wheel-metadata/ 24 | share/python-wheels/ 25 | *.egg-info/ 26 | .installed.cfg 27 | *.egg 28 | MANIFEST 29 | 30 | # PyInstaller 31 | # Usually these files are written by a python script from a template 32 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 33 | *.manifest 34 | *.spec 35 | 36 | # Installer logs 37 | pip-log.txt 38 | pip-delete-this-directory.txt 39 | 40 | # Unit test / coverage reports 41 | htmlcov/ 42 | .tox/ 43 | .nox/ 44 | .coverage 45 | .coverage.* 46 | .cache 47 | nosetests.xml 48 | coverage.xml 49 | *.cover 50 | *.py,cover 51 | .hypothesis/ 52 | .pytest_cache/ 53 | 54 | # Translations 55 | *.mo 56 | *.pot 57 | 58 | # Django stuff: 59 | *.log 60 | local_settings.py 61 | db.sqlite3 62 | db.sqlite3-journal 63 | 64 | # Flask stuff: 65 | instance/ 66 | .webassets-cache 67 | 68 | # Scrapy stuff: 69 | .scrapy 70 | 71 | # Sphinx documentation 72 | docs/_build/ 73 | 74 | # PyBuilder 75 | target/ 76 | 77 | # Jupyter Notebook 78 | .ipynb_checkpoints 79 | 80 | # IPython 81 | profile_default/ 82 | ipython_config.py 83 | 84 | # pyenv 85 | .python-version 86 | 87 | # pipenv 88 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 89 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 90 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 91 | # install all needed dependencies. 92 | #Pipfile.lock 93 | 94 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow 95 | __pypackages__/ 96 | 97 | # Celery stuff 98 | celerybeat-schedule 99 | celerybeat.pid 100 | 101 | # SageMath parsed files 102 | *.sage.py 103 | 104 | # Environments 105 | .env 106 | .venv 107 | env/ 108 | venv/ 109 | ENV/ 110 | env.bak/ 111 | venv.bak/ 112 | 113 | # Spyder project settings 114 | .spyderproject 115 | .spyproject 116 | 117 | # Rope project settings 118 | .ropeproject 119 | 120 | # mkdocs documentation 121 | /site 122 | 123 | # mypy 124 | .mypy_cache/ 125 | .dmypy.json 126 | dmypy.json 127 | 128 | # Pyre type checker 129 | .pyre/ 130 | -------------------------------------------------------------------------------- /Jupyter/RL_shower.ipynb: -------------------------------------------------------------------------------- 1 | {"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"name":"OG_SH_DQN.ipynb","provenance":[],"collapsed_sections":[],"machine_shape":"hm","authorship_tag":"ABX9TyPQ4BKbmrmCOHTGWU8hERgU"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"},"accelerator":"GPU"},"cells":[{"cell_type":"markdown","source":["# 0. Install Dependencies"],"metadata":{"id":"uqPQc2mVp1XU"}},{"cell_type":"code","source":["# Install Dependencies\n","!pip install keras-rl2"],"metadata":{"id":"Qma6ADIS-AuQ","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1649392591926,"user_tz":-540,"elapsed":3598,"user":{"displayName":"youngwoo Oh","userId":"06892641019570208070"}},"outputId":"85ab8a69-bbf3-454b-89e6-69b288791e67"},"execution_count":1,"outputs":[{"output_type":"stream","name":"stdout","text":["Collecting keras-rl2\n"," Downloading keras_rl2-1.0.5-py3-none-any.whl (52 kB)\n","\u001b[?25l\r\u001b[K |██████▎ | 10 kB 35.4 MB/s eta 0:00:01\r\u001b[K |████████████▋ | 20 kB 8.9 MB/s eta 0:00:01\r\u001b[K |██████████████████▉ | 30 kB 7.8 MB/s eta 0:00:01\r\u001b[K |█████████████████████████▏ | 40 kB 7.4 MB/s eta 0:00:01\r\u001b[K |███████████████████████████████▍| 51 kB 4.1 MB/s eta 0:00:01\r\u001b[K |████████████████████████████████| 52 kB 936 kB/s \n","\u001b[?25hRequirement already satisfied: tensorflow in /usr/local/lib/python3.7/dist-packages (from keras-rl2) (2.8.0)\n","Requirement already satisfied: tensorflow-io-gcs-filesystem>=0.23.1 in /usr/local/lib/python3.7/dist-packages (from tensorflow->keras-rl2) (0.24.0)\n","Requirement already satisfied: absl-py>=0.4.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow->keras-rl2) (1.0.0)\n","Requirement already satisfied: h5py>=2.9.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow->keras-rl2) (3.1.0)\n","Requirement already satisfied: numpy>=1.20 in /usr/local/lib/python3.7/dist-packages (from tensorflow->keras-rl2) (1.21.5)\n","Requirement already satisfied: tensorboard<2.9,>=2.8 in /usr/local/lib/python3.7/dist-packages (from tensorflow->keras-rl2) (2.8.0)\n","Requirement already satisfied: grpcio<2.0,>=1.24.3 in /usr/local/lib/python3.7/dist-packages (from tensorflow->keras-rl2) (1.44.0)\n","Requirement already satisfied: astunparse>=1.6.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow->keras-rl2) (1.6.3)\n","Collecting tf-estimator-nightly==2.8.0.dev2021122109\n"," Downloading tf_estimator_nightly-2.8.0.dev2021122109-py2.py3-none-any.whl (462 kB)\n","\u001b[K |████████████████████████████████| 462 kB 7.6 MB/s \n","\u001b[?25hRequirement already satisfied: libclang>=9.0.1 in /usr/local/lib/python3.7/dist-packages (from tensorflow->keras-rl2) (13.0.0)\n","Requirement already satisfied: typing-extensions>=3.6.6 in /usr/local/lib/python3.7/dist-packages (from tensorflow->keras-rl2) (3.10.0.2)\n","Requirement already satisfied: protobuf>=3.9.2 in /usr/local/lib/python3.7/dist-packages (from tensorflow->keras-rl2) (3.17.3)\n","Requirement already satisfied: setuptools in /usr/local/lib/python3.7/dist-packages (from tensorflow->keras-rl2) (57.4.0)\n","Requirement already satisfied: gast>=0.2.1 in /usr/local/lib/python3.7/dist-packages (from tensorflow->keras-rl2) (0.5.3)\n","Requirement already satisfied: google-pasta>=0.1.1 in /usr/local/lib/python3.7/dist-packages (from tensorflow->keras-rl2) (0.2.0)\n","Requirement already satisfied: six>=1.12.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow->keras-rl2) (1.15.0)\n","Requirement already satisfied: wrapt>=1.11.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow->keras-rl2) (1.14.0)\n","Requirement already satisfied: keras-preprocessing>=1.1.1 in /usr/local/lib/python3.7/dist-packages (from tensorflow->keras-rl2) (1.1.2)\n","Requirement already satisfied: termcolor>=1.1.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow->keras-rl2) (1.1.0)\n","Requirement already satisfied: opt-einsum>=2.3.2 in /usr/local/lib/python3.7/dist-packages (from tensorflow->keras-rl2) (3.3.0)\n","Requirement already satisfied: flatbuffers>=1.12 in /usr/local/lib/python3.7/dist-packages (from tensorflow->keras-rl2) (2.0)\n","Requirement already satisfied: keras<2.9,>=2.8.0rc0 in /usr/local/lib/python3.7/dist-packages (from tensorflow->keras-rl2) (2.8.0)\n","Requirement already satisfied: wheel<1.0,>=0.23.0 in /usr/local/lib/python3.7/dist-packages (from astunparse>=1.6.0->tensorflow->keras-rl2) (0.37.1)\n","Requirement already satisfied: cached-property in /usr/local/lib/python3.7/dist-packages (from h5py>=2.9.0->tensorflow->keras-rl2) (1.5.2)\n","Requirement already satisfied: google-auth-oauthlib<0.5,>=0.4.1 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.9,>=2.8->tensorflow->keras-rl2) (0.4.6)\n","Requirement already satisfied: google-auth<3,>=1.6.3 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.9,>=2.8->tensorflow->keras-rl2) (1.35.0)\n","Requirement already satisfied: requests<3,>=2.21.0 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.9,>=2.8->tensorflow->keras-rl2) (2.23.0)\n","Requirement already satisfied: tensorboard-plugin-wit>=1.6.0 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.9,>=2.8->tensorflow->keras-rl2) (1.8.1)\n","Requirement already satisfied: werkzeug>=0.11.15 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.9,>=2.8->tensorflow->keras-rl2) (1.0.1)\n","Requirement already satisfied: tensorboard-data-server<0.7.0,>=0.6.0 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.9,>=2.8->tensorflow->keras-rl2) (0.6.1)\n","Requirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.9,>=2.8->tensorflow->keras-rl2) (3.3.6)\n","Requirement already satisfied: rsa<5,>=3.1.4 in /usr/local/lib/python3.7/dist-packages (from google-auth<3,>=1.6.3->tensorboard<2.9,>=2.8->tensorflow->keras-rl2) (4.8)\n","Requirement already satisfied: cachetools<5.0,>=2.0.0 in /usr/local/lib/python3.7/dist-packages (from google-auth<3,>=1.6.3->tensorboard<2.9,>=2.8->tensorflow->keras-rl2) (4.2.4)\n","Requirement already satisfied: pyasn1-modules>=0.2.1 in /usr/local/lib/python3.7/dist-packages (from google-auth<3,>=1.6.3->tensorboard<2.9,>=2.8->tensorflow->keras-rl2) (0.2.8)\n","Requirement already satisfied: requests-oauthlib>=0.7.0 in /usr/local/lib/python3.7/dist-packages (from google-auth-oauthlib<0.5,>=0.4.1->tensorboard<2.9,>=2.8->tensorflow->keras-rl2) (1.3.1)\n","Requirement already satisfied: importlib-metadata>=4.4 in /usr/local/lib/python3.7/dist-packages (from markdown>=2.6.8->tensorboard<2.9,>=2.8->tensorflow->keras-rl2) (4.11.3)\n","Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.7/dist-packages (from importlib-metadata>=4.4->markdown>=2.6.8->tensorboard<2.9,>=2.8->tensorflow->keras-rl2) (3.7.0)\n","Requirement already satisfied: pyasn1<0.5.0,>=0.4.6 in /usr/local/lib/python3.7/dist-packages (from pyasn1-modules>=0.2.1->google-auth<3,>=1.6.3->tensorboard<2.9,>=2.8->tensorflow->keras-rl2) (0.4.8)\n","Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.7/dist-packages (from requests<3,>=2.21.0->tensorboard<2.9,>=2.8->tensorflow->keras-rl2) (1.24.3)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.7/dist-packages (from requests<3,>=2.21.0->tensorboard<2.9,>=2.8->tensorflow->keras-rl2) (2021.10.8)\n","Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.7/dist-packages (from requests<3,>=2.21.0->tensorboard<2.9,>=2.8->tensorflow->keras-rl2) (2.10)\n","Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.7/dist-packages (from requests<3,>=2.21.0->tensorboard<2.9,>=2.8->tensorflow->keras-rl2) (3.0.4)\n","Requirement already satisfied: oauthlib>=3.0.0 in /usr/local/lib/python3.7/dist-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<0.5,>=0.4.1->tensorboard<2.9,>=2.8->tensorflow->keras-rl2) (3.2.0)\n","Installing collected packages: tf-estimator-nightly, keras-rl2\n","Successfully installed keras-rl2-1.0.5 tf-estimator-nightly-2.8.0.dev2021122109\n"]}]},{"cell_type":"code","source":["# Test Random Environment with OpenAI Gym\n","import math\n","import cmath\n","import random\n","import itertools\n","import tensorflow\n","import numpy as np\n","\n","from gym import Env\n","from matplotlib import cm\n","from scipy.constants import *\n","from matplotlib import colors\n","from rl.agents import DQNAgent\n","\n","import matplotlib.pyplot as plt\n","\n","from gym.spaces import Discrete, Box\n","from rl.policy import BoltzmannQPolicy\n","from rl.memory import SequentialMemory\n","from mpl_toolkits.mplot3d import Axes3D\n","from tensorflow.keras.optimizers import Adam\n","from tensorflow.keras.layers import Dense, Flatten"],"metadata":{"id":"fowtB78oAg_R","executionInfo":{"status":"ok","timestamp":1649392631599,"user_tz":-540,"elapsed":2994,"user":{"displayName":"youngwoo Oh","userId":"06892641019570208070"}}},"execution_count":2,"outputs":[]},{"cell_type":"markdown","source":["# 1. Test Random Environment with OpenAI Gym"],"metadata":{"id":"UbPLWxH1p5r-"}},{"cell_type":"code","source":["class ShowerEnv(Env):\n"," def __init__(self):\n","\n"," self.action_space = Discrete(3)\n","\n"," self.observation_space = Box(low=np.array([0]), high=np.array([100]))\n","\n"," self.state = 38 + random.randint(-3,3)\n","\n"," self.shower_length = 60\n"," \n"," def step(self, action):\n","\n"," self.state += action -1 \n"," self.shower_length -= 1 \n"," \n"," # Calculate reward\n"," if self.state >=37 and self.state <=39: \n"," reward =1 \n"," else: \n"," reward = -1 \n"," \n"," # Check if shower is done\n"," if self.shower_length <= 0: \n"," done = True\n"," else:\n"," done = False\n"," \n"," info = {}\n"," \n"," return self.state, reward, done, info\n","\n"," def render(self):\n"," pass\n"," \n"," def reset(self):\n","\n"," self.state = 38 + random.randint(-3,3)\n"," \n"," self.shower_length = 60 \n"," return self.state\n"," "],"metadata":{"id":"5uIWNwsTDrJX","executionInfo":{"status":"ok","timestamp":1649392749998,"user_tz":-540,"elapsed":383,"user":{"displayName":"youngwoo Oh","userId":"06892641019570208070"}}},"execution_count":8,"outputs":[]},{"cell_type":"code","source":["env = ShowerEnv()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"JWe2MAX9LvDO","executionInfo":{"status":"ok","timestamp":1649392752269,"user_tz":-540,"elapsed":401,"user":{"displayName":"youngwoo Oh","userId":"06892641019570208070"}},"outputId":"5b2020f9-107f-4e07-bec4-cf2bfa59223c"},"execution_count":9,"outputs":[{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.7/dist-packages/gym/logger.py:30: UserWarning: \u001b[33mWARN: Box bound precision lowered by casting to float32\u001b[0m\n"," warnings.warn(colorize('%s: %s'%('WARN', msg % args), 'yellow'))\n"]}]},{"cell_type":"code","source":["# test of action space\n","print(env.action_space) # action space list\n","print(env.action_space.n) # random\n","print(type(env.action_space)) # action types\n","\n","# test of observation space\n","print(env.observation_space) # observation values\n","print(type(env.observation_space)) # observation types\n","\n","# test of state\n","print(env.state)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"aS-qcwR9Lygr","executionInfo":{"status":"ok","timestamp":1649392754125,"user_tz":-540,"elapsed":4,"user":{"displayName":"youngwoo Oh","userId":"06892641019570208070"}},"outputId":"a86e0c09-f333-496e-c979-6dbb5dd30dc0"},"execution_count":10,"outputs":[{"output_type":"stream","name":"stdout","text":["Discrete(3)\n","3\n","\n","Box(0.0, 100.0, (1,), float32)\n","\n","40\n"]}]},{"cell_type":"code","source":["episodes = 10\n","for episode in range(1, episodes+1):\n"," state = env.reset()\n"," done = False\n"," score = 0 \n"," states = env.observation_space.shape\n"," state = np.reshape(state, states)\n","\n"," print(states)\n"," print(state)\n"," \n"," while not done:\n"," #env.render()\n"," action = env.action_space.sample()\n"," n_state, reward, done, info = env.step(action)\n"," score+=reward\n"," print('Episode:{} Score:{}'.format(episode, score))"],"metadata":{"id":"8FL9GvwGAqOx","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1649392861094,"user_tz":-540,"elapsed":395,"user":{"displayName":"youngwoo Oh","userId":"06892641019570208070"}},"outputId":"bee16bfc-38e6-4213-8185-62522a285f3c"},"execution_count":16,"outputs":[{"output_type":"stream","name":"stdout","text":["(1,)\n","[0]\n","Episode:1 Score:-60\n","(1,)\n","[0]\n","Episode:2 Score:-60\n","(1,)\n","[0]\n","Episode:3 Score:-60\n","(1,)\n","[0]\n","Episode:4 Score:-60\n","(1,)\n","[0]\n","Episode:5 Score:-60\n","(1,)\n","[0]\n","Episode:6 Score:-60\n","(1,)\n","[0]\n","Episode:7 Score:-60\n","(1,)\n","[0]\n","Episode:8 Score:-60\n","(1,)\n","[0]\n","Episode:9 Score:-60\n","(1,)\n","[0]\n","Episode:10 Score:-60\n"]}]},{"cell_type":"code","source":["# test section\n","states = env.observation_space.shape\n","actions = env.action_space.n\n","\n","state = np.reshape(state, states)\n","\n","print(states)\n","print(state)\n","\n","print(env.observation_space)\n","print(actions)"],"metadata":{"id":"IFBtGuCbSImX","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1649392837888,"user_tz":-540,"elapsed":529,"user":{"displayName":"youngwoo Oh","userId":"06892641019570208070"}},"outputId":"3c61ef33-0934-4e2f-94b2-b3286de85206"},"execution_count":12,"outputs":[{"output_type":"stream","name":"stdout","text":["(1,)\n","[0]\n","Box(0.0, 100.0, (1,), float32)\n","3\n"]}]},{"cell_type":"code","source":["# model = tensorflow.keras.Sequential() \n","def build_model(states, actions):\n"," model = tensorflow.keras.Sequential() \n"," model.add(Dense(24, activation='relu', input_shape=states))\n"," model.add(Dense(24, activation='relu'))\n"," model.add(Dense(actions, activation='linear'))\n"," return model"],"metadata":{"id":"uSZiQiC8Aub7","executionInfo":{"status":"ok","timestamp":1649392850284,"user_tz":-540,"elapsed":405,"user":{"displayName":"youngwoo Oh","userId":"06892641019570208070"}}},"execution_count":13,"outputs":[]},{"cell_type":"code","source":["model = build_model(states, actions)"],"metadata":{"id":"YUPNnbg6Avo7","executionInfo":{"status":"ok","timestamp":1649392852728,"user_tz":-540,"elapsed":373,"user":{"displayName":"youngwoo Oh","userId":"06892641019570208070"}}},"execution_count":14,"outputs":[]},{"cell_type":"code","source":["model.summary()\n","\n","print(model.output_shape)\n","print(actions)"],"metadata":{"id":"0awwUvQ9AwUr","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1649392853157,"user_tz":-540,"elapsed":10,"user":{"displayName":"youngwoo Oh","userId":"06892641019570208070"}},"outputId":"6b54f70b-449a-480e-fe76-fc470567482c"},"execution_count":15,"outputs":[{"output_type":"stream","name":"stdout","text":["Model: \"sequential\"\n","_________________________________________________________________\n"," Layer (type) Output Shape Param # \n","=================================================================\n"," dense (Dense) (None, 24) 48 \n"," \n"," dense_1 (Dense) (None, 24) 600 \n"," \n"," dense_2 (Dense) (None, 3) 75 \n"," \n","=================================================================\n","Total params: 723\n","Trainable params: 723\n","Non-trainable params: 0\n","_________________________________________________________________\n","(None, 3)\n","3\n"]}]},{"cell_type":"markdown","source":["# 3. Build Agent with Keras-RL"],"metadata":{"id":"GSRhMP8aqBXl"}},{"cell_type":"code","source":["def build_agent(model, actions):\n"," policy = BoltzmannQPolicy()\n"," memory = SequentialMemory(limit=50000, window_length=1)\n"," dqn = DQNAgent(model=model, memory=memory, policy=policy, \n"," nb_actions=actions, nb_steps_warmup=10, target_model_update=1e-2)\n"," return dqn"],"metadata":{"id":"sWnDzWsPA0H7","executionInfo":{"status":"ok","timestamp":1649392865305,"user_tz":-540,"elapsed":410,"user":{"displayName":"youngwoo Oh","userId":"06892641019570208070"}}},"execution_count":17,"outputs":[]},{"cell_type":"code","source":["dqn = build_agent(model, actions)\n","dqn.compile(Adam(learning_rate=1e-3), metrics=['mae'])\n","dqn.fit(env, nb_steps=10000, visualize=False, verbose=1)"],"metadata":{"id":"39mfM7A1A1QM"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["scores = dqn.test(env, nb_episodes=100, visualize=False)\n","print(np.mean(scores.history['episode_reward']))"],"metadata":{"id":"hCZAygNhA2NE"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["_ = dqn.test(env, nb_episodes=15, visualize=False)"],"metadata":{"id":"wHmN5pSRJ94w"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":["# 4. Reloading Agent from Memory"],"metadata":{"id":"Xvgrcy9UqGVW"}},{"cell_type":"code","source":["dqn.save_weights('dqn_weights.h5f', overwrite=True)"],"metadata":{"id":"Ci1rsvQfA3ZE"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["del model\n","del dqn\n","del env"],"metadata":{"id":"KmMLlMTRA6Fw"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["dqn.load_weights('dqn_weights.h5f')"],"metadata":{"id":"Zeo8MlXYA7qF"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["_ = dqn.test(env, nb_episodes=5, visualize=False)"],"metadata":{"id":"hqgAKpZiA783","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1649229758325,"user_tz":-540,"elapsed":409,"user":{"displayName":"youngwoo Oh","userId":"06892641019570208070"}},"outputId":"9916c0cd-875e-4083-ea77-c708cd9e0369"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Testing for 5 episodes ...\n","Episode 1: reward: -60.000, steps: 60\n","Episode 2: reward: -54.000, steps: 60\n","Episode 3: reward: -60.000, steps: 60\n","Episode 4: reward: -58.000, steps: 60\n","Episode 5: reward: -54.000, steps: 60\n"]}]}]} -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | MIT License 2 | 3 | Copyright (c) 2022 FIVEYOUNGWOO 4 | 5 | Permission is hereby granted, free of charge, to any person obtaining a copy 6 | of this software and associated documentation files (the "Software"), to deal 7 | in the Software without restriction, including without limitation the rights 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell 9 | copies of the Software, and to permit persons to whom the Software is 10 | furnished to do so, subject to the following conditions: 11 | 12 | The above copyright notice and this permission notice shall be included in all 13 | copies or substantial portions of the Software. 14 | 15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE 21 | SOFTWARE. 22 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | ## Simple-Reinforcement-Learning-Example 2 | 3 | Implementation of DRL logics-based stable water temperature game. 4 | 5 | The game gives some insight into reinforcement learning. --------------------------------------------------------------------------------