├── .gitignore ├── LICENSE ├── README.md ├── basic ├── test_ray_air.py ├── test_ray_core.py ├── test_ray_rllib.py ├── test_ray_train.py └── test_ray_tune.py ├── ray_core_tutorial └── ray_core_tasks.py └── rllib_tutorial ├── rllib_60seconds.py ├── rllib_basic_usage.py └── rllib_config.py /.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 | share/python-wheels/ 24 | *.egg-info/ 25 | .installed.cfg 26 | *.egg 27 | MANIFEST 28 | 29 | # PyInstaller 30 | # Usually these files are written by a python script from a template 31 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 32 | *.manifest 33 | *.spec 34 | 35 | # Installer logs 36 | pip-log.txt 37 | pip-delete-this-directory.txt 38 | 39 | # Unit test / coverage reports 40 | htmlcov/ 41 | .tox/ 42 | .nox/ 43 | .coverage 44 | .coverage.* 45 | .cache 46 | nosetests.xml 47 | coverage.xml 48 | *.cover 49 | *.py,cover 50 | .hypothesis/ 51 | .pytest_cache/ 52 | cover/ 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 | .pybuilder/ 76 | target/ 77 | 78 | # Jupyter Notebook 79 | .ipynb_checkpoints 80 | 81 | # IPython 82 | profile_default/ 83 | ipython_config.py 84 | 85 | # pyenv 86 | # For a library or package, you might want to ignore these files since the code is 87 | # intended to run in multiple environments; otherwise, check them in: 88 | # .python-version 89 | 90 | # pipenv 91 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 92 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 93 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 94 | # install all needed dependencies. 95 | #Pipfile.lock 96 | 97 | # poetry 98 | # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. 99 | # This is especially recommended for binary packages to ensure reproducibility, and is more 100 | # commonly ignored for libraries. 101 | # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control 102 | #poetry.lock 103 | 104 | # pdm 105 | # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. 106 | #pdm.lock 107 | # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it 108 | # in version control. 109 | # https://pdm.fming.dev/#use-with-ide 110 | .pdm.toml 111 | 112 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm 113 | __pypackages__/ 114 | 115 | # Celery stuff 116 | celerybeat-schedule 117 | celerybeat.pid 118 | 119 | # SageMath parsed files 120 | *.sage.py 121 | 122 | # Environments 123 | .env 124 | .venv 125 | env/ 126 | venv/ 127 | ENV/ 128 | env.bak/ 129 | venv.bak/ 130 | 131 | # Spyder project settings 132 | .spyderproject 133 | .spyproject 134 | 135 | # Rope project settings 136 | .ropeproject 137 | 138 | # mkdocs documentation 139 | /site 140 | 141 | # mypy 142 | .mypy_cache/ 143 | .dmypy.json 144 | dmypy.json 145 | 146 | # Pyre type checker 147 | .pyre/ 148 | 149 | # pytype static type analyzer 150 | .pytype/ 151 | 152 | # Cython debug symbols 153 | cython_debug/ 154 | 155 | # PyCharm 156 | # JetBrains specific template is maintained in a separate JetBrains.gitignore that can 157 | # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore 158 | # and can be added to the global gitignore or merged into this file. For a more nuclear 159 | # option (not recommended) you can uncomment the following to ignore the entire idea folder. 160 | #.idea/ 161 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Ray Tutorial 2 | 3 | 4 | Ray是一个开源的分布式机器学习框架，不仅拥有高效的分布式训练能力，也有丰富的机器学习应用，极大地降低了大规模机器学习的门槛。Ray有诸多模块，包括实现基本分布式能力的Ray Core，进行数据处理的Ray Data，进行训练的Ray Train，超参数调整的Ray Tune，实现推理的Ray Serve，强化学习库Ray RLlib，以及集合了多种功能的上层机器学习API Ray AIR。 5 | 6 | 7 | 8 | ## Ray使用教程（一）：基本用法 9 | 10 | 详见知乎教程：[Ray使用教程（一）：基本用法](https://zhuanlan.zhihu.com/p/639768943) 11 | 12 | 代码：[basic](https://github.com/OpenRL-Lab/Ray_Tutorial/tree/main/basic) 13 | 14 | 15 | 16 | ## Citing Ray_Tutorial 17 | 18 | If you use Ray_Tutorial in your work, please cite us: 19 | 20 | ``` 21 | @article{openrl2023Ray_Tutorial, 22 | title={Ray Tutorial}, 23 | author={OpenRL Contributors}, 24 | year={2023}, 25 | howpublished={\url{https://github.com/OpenRL-Lab/Ray_Tutorial/}}, 26 | } 27 | ``` 28 | -------------------------------------------------------------------------------- /basic/test_ray_air.py: -------------------------------------------------------------------------------- 1 | import ray 2 | from ray.data.preprocessors import StandardScaler 3 | from ray.air.config import ScalingConfig 4 | from ray.train.xgboost import XGBoostTrainer 5 | 6 | 7 | # Load data. 8 | dataset = ray.data.read_csv("s3://anonymous@air-example-data/breast_cancer.csv") 9 | 10 | # Split data into train and validation. 11 | train_dataset, valid_dataset = dataset.train_test_split(test_size=0.3) 12 | 13 | # Create a test dataset by dropping the target column. 14 | test_dataset = valid_dataset.drop_columns(cols=["target"]) 15 | 16 | # Create a preprocessor to scale some columns. 17 | preprocessor = StandardScaler(columns=["mean radius", "mean texture"]) 18 | 19 | # Create a XGBoost trainer 20 | trainer = XGBoostTrainer( 21 | scaling_config=ScalingConfig( 22 | # Number of workers to use for data parallelism. 23 | num_workers=2, 24 | # Whether to use GPU acceleration. 25 | use_gpu=False, 26 | # Make sure to leave some CPUs free for Ray Data operations. 27 | _max_cpu_fraction_per_node=0.9, 28 | ), 29 | label_column="target", 30 | num_boost_round=20, 31 | params={ 32 | # XGBoost specific params 33 | "objective": "binary:logistic", 34 | # "tree_method": "gpu_hist", # uncomment this to use GPUs. 35 | "eval_metric": ["logloss", "error"], 36 | }, 37 | datasets={"train": train_dataset, "valid": valid_dataset}, 38 | preprocessor=preprocessor, 39 | ) 40 | result = trainer.fit() 41 | print(result.metrics) -------------------------------------------------------------------------------- /basic/test_ray_core.py: -------------------------------------------------------------------------------- 1 | import ray 2 | 3 | 4 | ray.init() 5 | @ray.remote 6 | def f(x): 7 | return x * x 8 | 9 | 10 | futures = [f.remote(i) for i in range(4)] 11 | print(ray.get(futures)) # [0, 1, 4, 9] 12 | 13 | 14 | @ray.remote 15 | class Counter(object): 16 | def __init__(self): 17 | self.n = 0 18 | 19 | def increment(self): 20 | self.n += 1 21 | 22 | def read(self): 23 | return self.n 24 | 25 | 26 | RAY_DEDUP_LOGS=0 27 | counters = [Counter.remote() for i in range(4)] 28 | [c.increment.remote() for c in counters] 29 | futures = [c.read.remote() for c in counters] 30 | print(ray.get(futures)) # [1, 1, 1, 1] 31 | 32 | ray.shutdown() -------------------------------------------------------------------------------- /basic/test_ray_rllib.py: -------------------------------------------------------------------------------- 1 | from ray.rllib.algorithms.ppo import PPOConfig 2 | 3 | config = ( # 1. Configure the algorithm, 4 | PPOConfig() 5 | .environment("Taxi-v3") 6 | .rollouts(num_rollout_workers=2) 7 | .framework("torch") 8 | .training(model={"fcnet_hiddens": [64, 64]}) 9 | .evaluation(evaluation_num_workers=1) 10 | ) 11 | 12 | algo = config.build() # 2. build the algorithm, 13 | 14 | for _ in range(10): 15 | result = algo.train() 16 | print("episode mean reward: ", result["episode_reward_mean"] ) # 3. train it, 17 | 18 | algo.evaluate() # 4. and evaluate it. -------------------------------------------------------------------------------- /basic/test_ray_train.py: -------------------------------------------------------------------------------- 1 | import torch 2 | import torch.nn as nn 3 | from torch.utils.data import DataLoader 4 | from torchvision import datasets 5 | from torchvision.transforms import ToTensor 6 | 7 | from ray import train 8 | from ray.train.torch import TorchTrainer 9 | from ray.train import ScalingConfig 10 | 11 | 12 | def get_dataset(): 13 | return datasets.FashionMNIST( 14 | root="/tmp/data", 15 | train=True, 16 | download=True, 17 | transform=ToTensor(), 18 | ) 19 | 20 | 21 | class NeuralNetwork(nn.Module): 22 | def __init__(self): 23 | super().__init__() 24 | self.flatten = nn.Flatten() 25 | self.linear_relu_stack = nn.Sequential( 26 | nn.Linear(28 * 28, 512), 27 | nn.ReLU(), 28 | nn.Linear(512, 512), 29 | nn.ReLU(), 30 | nn.Linear(512, 10), 31 | ) 32 | 33 | def forward(self, inputs): 34 | inputs = self.flatten(inputs) 35 | logits = self.linear_relu_stack(inputs) 36 | return logits 37 | 38 | 39 | # without distributed training, pure pytorch 40 | def train_func(): 41 | num_epochs = 3 42 | batch_size = 64 43 | 44 | dataset = get_dataset() 45 | dataloader = DataLoader(dataset, batch_size=batch_size) 46 | 47 | model = NeuralNetwork() 48 | 49 | criterion = nn.CrossEntropyLoss() 50 | optimizer = torch.optim.SGD(model.parameters(), lr=0.01) 51 | 52 | for epoch in range(num_epochs): 53 | for inputs, labels in dataloader: 54 | optimizer.zero_grad() 55 | pred = model(inputs) 56 | loss = criterion(pred, labels) 57 | loss.backward() 58 | optimizer.step() 59 | print(f"epoch: {epoch}, loss: {loss.item()}") 60 | 61 | 62 | # train_func() 63 | 64 | 65 | # distributed training 66 | def train_func_distributed(): 67 | num_epochs = 3 68 | batch_size = 64 69 | 70 | dataset = get_dataset() 71 | dataloader = DataLoader(dataset, batch_size=batch_size) 72 | dataloader = train.torch.prepare_data_loader(dataloader) 73 | 74 | model = NeuralNetwork() 75 | model = train.torch.prepare_model(model) 76 | 77 | criterion = nn.CrossEntropyLoss() 78 | optimizer = torch.optim.SGD(model.parameters(), lr=0.01) 79 | 80 | for epoch in range(num_epochs): 81 | for inputs, labels in dataloader: 82 | optimizer.zero_grad() 83 | pred = model(inputs) 84 | loss = criterion(pred, labels) 85 | loss.backward() 86 | optimizer.step() 87 | print(f"epoch: {epoch}, loss: {loss.item()}") 88 | 89 | 90 | # For GPU Training, set `use_gpu` to True. 91 | use_gpu = False 92 | 93 | trainer = TorchTrainer( 94 | train_func_distributed, 95 | scaling_config=ScalingConfig(num_workers=4, use_gpu=use_gpu) 96 | ) 97 | 98 | results = trainer.fit() -------------------------------------------------------------------------------- /basic/test_ray_tune.py: -------------------------------------------------------------------------------- 1 | from ray import tune 2 | 3 | 4 | def objective(config): 5 | score = config["a"] ** 2 + config["b"] 6 | return {"score": score} 7 | 8 | 9 | search_space = { 10 | "a": tune.grid_search([0.001, 0.01, 0.1, 1.0]), 11 | "b": tune.choice([1, 2, 3]), 12 | } 13 | 14 | tuner = tune.Tuner(objective, param_space=search_space) 15 | 16 | results = tuner.fit() 17 | print(results.get_best_result(metric="score", mode="min").config) -------------------------------------------------------------------------------- /ray_core_tutorial/ray_core_tasks.py: -------------------------------------------------------------------------------- 1 | import ray 2 | import time 3 | 4 | 5 | # A regular Python function. 6 | def normal_function(): 7 | return 1 8 | 9 | 10 | # By adding the `@ray.remote` decorator, a regular Python function 11 | # becomes a Ray remote function. 12 | @ray.remote 13 | def my_function(): 14 | return 1 15 | 16 | 17 | # To invoke this remote function, use the `remote` method. 18 | # This will immediately return an object ref (a future) and then create 19 | # a task that will be executed on a worker process. 20 | obj_ref = my_function.remote() 21 | 22 | # The result can be retrieved with ``ray.get``. 23 | assert ray.get(obj_ref) == 1 24 | 25 | 26 | @ray.remote 27 | def slow_function(): 28 | time.sleep(10) 29 | return 1 30 | 31 | 32 | # Ray tasks are executed in parallel. 33 | # All computation is performed in the background, driven by Ray's internal event loop. 34 | for _ in range(4): 35 | # This doesn't block. 36 | slow_function.remote() 37 | 38 | 39 | # Specify required resources. 40 | @ray.remote(num_cpus=4, num_gpus=2) 41 | def my_function(): 42 | return 1 43 | 44 | 45 | # Override the default resource requirements. 46 | my_function.options(num_cpus=3).remote() 47 | 48 | 49 | @ray.remote 50 | def function_with_an_argument(value): 51 | return value + 1 52 | 53 | 54 | obj_ref1 = my_function.remote() 55 | assert ray.get(obj_ref1) == 1 56 | 57 | # You can pass an object ref as an argument to another Ray task. 58 | obj_ref2 = function_with_an_argument.remote(obj_ref1) 59 | assert ray.get(obj_ref2) == 2 60 | 61 | 62 | object_refs = [slow_function.remote() for _ in range(2)] 63 | # Return as soon as one of the tasks finished execution. 64 | ready_refs, remaining_refs = ray.wait(object_refs, num_returns=1, timeout=None) -------------------------------------------------------------------------------- /rllib_tutorial/rllib_60seconds.py: -------------------------------------------------------------------------------- 1 | from ray.rllib.algorithms.ppo import PPOConfig 2 | 3 | config = ( # 1. Configure the algorithm, 4 | PPOConfig() 5 | .environment("Taxi-v3") 6 | .rollouts(num_rollout_workers=2) 7 | .framework("torch") 8 | .training(model={"fcnet_hiddens": [64, 64]}) 9 | .evaluation(evaluation_num_workers=1) 10 | ) 11 | 12 | algo = config.build() # 2. build the algorithm, 13 | 14 | for _ in range(5): 15 | print(algo.train()) # 3. train it, 16 | 17 | algo.evaluate() # 4. and evaluate it. -------------------------------------------------------------------------------- /rllib_tutorial/rllib_basic_usage.py: -------------------------------------------------------------------------------- 1 | import ray 2 | from ray import air, tune 3 | from ray.rllib.algorithms.ppo import PPOConfig 4 | from ray.tune.logger import pretty_print 5 | 6 | # train 7 | # algo = ( 8 | # PPOConfig() 9 | # .rollouts(num_rollout_workers=1) 10 | # .framework("torch") 11 | # .resources(num_gpus=0) 12 | # .environment(env="CartPole-v1") 13 | # .build() 14 | # ) 15 | # 16 | # for i in range(10): 17 | # result = algo.train() 18 | # print(pretty_print(result)) 19 | # 20 | # if i % 5 == 0: 21 | # checkpoint_dir = algo.save() 22 | # print(f"Checkpoint saved in directory {checkpoint_dir}") 23 | 24 | 25 | # tune 26 | ray.init() 27 | 28 | config = PPOConfig()\ 29 | .training(lr=tune.grid_search([0.01, 0.001, 0.0001]))\ 30 | .framework("torch")\ 31 | .environment(env="CartPole-v1") 32 | 33 | tuner = tune.Tuner( 34 | "PPO", 35 | run_config=air.RunConfig( 36 | stop={"episode_reward_mean": 150}, 37 | checkpoint_config=air.CheckpointConfig(checkpoint_at_end=True), 38 | ), 39 | param_space=config, 40 | ) 41 | 42 | results = tuner.fit() 43 | 44 | # Get the best result based on a particular metric. 45 | best_result = results.get_best_result(metric="episode_reward_mean", mode="max") 46 | 47 | # Get the best checkpoint corresponding to the best result. 48 | best_checkpoint = best_result.checkpoint 49 | 50 | # load checkpoint 51 | # from ray.rllib.algorithms.algorithm import Algorithm 52 | # algo = Algorithm.from_checkpoint(checkpoint_path) -------------------------------------------------------------------------------- /rllib_tutorial/rllib_config.py: -------------------------------------------------------------------------------- 1 | from ray.rllib.algorithms.ppo import PPOConfig 2 | from ray.tune.logger import pretty_print 3 | import time 4 | 5 | 6 | algo = ( 7 | PPOConfig() 8 | .rollouts(num_rollout_workers=1) 9 | .framework("torch") 10 | .resources(num_gpus=1) 11 | .environment(env="CartPole-v1") 12 | .build() 13 | ) 14 | 15 | for i in range(10): 16 | result = algo.train() 17 | print(pretty_print(result)) --------------------------------------------------------------------------------