Unity 机器学习代理工具包 (ML-Agents) 是一个开源项目,它使游戏和模拟能够作为训练智能代理的环境。
您最多选择25个主题 主题必须以中文或者字母或数字开头,可以包含连字符 (-),并且长度不得超过35个字符
 
 
 
 
 
Chris Elion 7353ad22 Merge remote-tracking branch 'origin/develop' into try-tf2-support 5 年前
.circleci Merge remote-tracking branch 'origin/develop' into try-tf2-support 5 年前
.github Merge remote-tracking branch 'origin/develop' into try-tf2-support 5 年前
.yamato Merge remote-tracking branch 'origin/develop' into try-tf2-support 5 年前
UnitySDK Merge remote-tracking branch 'origin/develop' into try-tf2-support 5 年前
config Merge remote-tracking branch 'origin/develop' into try-tf2-support 5 年前
demos Merge remote-tracking branch 'origin/develop' into try-tf2-support 5 年前
docs Merge remote-tracking branch 'origin/develop' into try-tf2-support 5 年前
gym-unity Merge remote-tracking branch 'origin/develop' into try-tf2-support 5 年前
ml-agents Merge remote-tracking branch 'origin/develop' into try-tf2-support 5 年前
ml-agents-envs Merge remote-tracking branch 'origin/develop' into try-tf2-support 5 年前
notebooks Merge remote-tracking branch 'origin/develop' into try-tf2-support 5 年前
protobuf-definitions Merge remote-tracking branch 'origin/develop' into try-tf2-support 5 年前
unity-volume [containerization] CPU based containerization to support all environments that don't use observations 7 年前
utils Merge remote-tracking branch 'origin/develop' into try-tf2-support 5 年前
.gitattributes Develop communicator redesign (#638) 7 年前
.gitignore python coverage: specify dirs, exclude test files (#2473) 5 年前
.pre-commit-config.yaml Allow usage with tensorflow 2.0.0 (via tf.compat.v1) (#2665) 5 年前
.pylintrc more pylint fixes (#2842) 5 年前
CODE_OF_CONDUCT.md Release v0.5 (#1202) 6 年前
CONTRIBUTING.md Update to include CLA language (#2195) 5 年前
Dockerfile Install dependencies for ml-agents-envs and ml-agents in Docker 6 年前
LICENSE Initial commit 7 年前
README.md Develop spawn brains (#2676) 5 年前
SURVEY.md fix trailing whitespace in markdown (#2786) 5 年前
markdown-link-check.fast.json [CI] filter remote links, setup nightly full check (#2811) 5 年前
markdown-link-check.full.json exclude bair.berkeley.edu temporarily (#2702) 5 年前
run-standalone-build-osx.sh Add more editor versions for testing. (#2809) 5 年前
run-tests-editmode-osx-editor.sh Add more editor versions for testing. (#2809) 5 年前
setup.cfg ban raw tensorflow imports 5 年前
test_constraints_max_tf1_version.txt 3rd circleci run 5 年前
test_constraints_max_tf2_version.txt cleanup 5 年前
test_constraints_min_version.txt Develop allow python 3.7 (#2544) 5 年前
test_requirements.txt Develop allow python 3.7 (#2544) 5 年前

README.md

Unity ML-Agents Toolkit (Beta)

docs badge license badge

The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source Unity plugin that enables games and simulations to serve as environments for training intelligent agents. Agents can be trained using reinforcement learning, imitation learning, neuroevolution, or other machine learning methods through a simple-to-use Python API. We also provide implementations (based on TensorFlow) of state-of-the-art algorithms to enable game developers and hobbyists to easily train intelligent agents for 2D, 3D and VR/AR games. These trained agents can be used for multiple purposes, including controlling NPC behavior (in a variety of settings such as multi-agent and adversarial), automated testing of game builds and evaluating different game design decisions pre-release. The ML-Agents toolkit is mutually beneficial for both game developers and AI researchers as it provides a central platform where advances in AI can be evaluated on Unity’s rich environments and then made accessible to the wider research and game developer communities.

Features

  • Unity environment control from Python
  • 10+ sample Unity environments
  • Two deep reinforcement learning algorithms, Proximal Policy Optimization (PPO) and Soft Actor-Critic (SAC)
  • Support for multiple environment configurations and training scenarios
  • Train memory-enhanced agents using deep reinforcement learning
  • Easily definable Curriculum Learning and Generalization scenarios
  • Built-in support for Imitation Learning
  • Flexible agent control with On Demand Decision Making
  • Visualizing network outputs within the environment
  • Simplified set-up with Docker
  • Wrap learning environments as a gym
  • Utilizes the Unity Inference Engine
  • Train using concurrent Unity environment instances

Documentation

Additional Resources

We have published a series of blog posts that are relevant for ML-Agents:

In addition to our own documentation, here are some additional, relevant articles:

Community and Feedback

The ML-Agents toolkit is an open-source project and we encourage and welcome contributions. If you wish to contribute, be sure to review our contribution guidelines and code of conduct.

If you run into any problems using the ML-Agents toolkit, submit an issue and make sure to include as much detail as possible.

Your opinion matters a great deal to us. Only by hearing your thoughts on the Unity ML-Agents Toolkit can we continue to improve and grow. Please take a few minutes to let us know about it.

For any other questions or feedback, connect directly with the ML-Agents team at ml-agents@unity3d.com.

Translations

To make the Unity ML-Agents toolkit accessible to the global research and Unity developer communities, we're attempting to create and maintain translations of our documentation. We've started with translating a subset of the documentation to one language (Chinese), but we hope to continue translating more pages and to other languages. Consequently, we welcome any enhancements and improvements from the community.

License

Apache License 2.0

Citation

If you use Unity or the ML-Agents Toolkit to conduct research, we ask that you cite the following paper as a reference:

Juliani, A., Berges, V., Vckay, E., Gao, Y., Henry, H., Mattar, M., Lange, D. (2018). Unity: A General Platform for Intelligent Agents. arXiv preprint arXiv:1809.02627. https://github.com/Unity-Technologies/ml-agents.