Repository files navigation

(latest release)(all releases)

The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-sourceproject that enables games and simulations to serve as environments fortraining intelligent agents. We provide implementations (based on PyTorch)of state-of-the-art algorithms to enable game developers and hobbyists to easilytrain intelligent agents for 2D, 3D and VR/AR games. Researchers can also use theprovided simple-to-use Python API to train Agents using reinforcement learning,imitation learning, neuroevolution, or any other methods. These trained agents can beused for multiple purposes, including controlling NPC behavior (in a variety ofsettings such as multi-agent and adversarial), automated testing of game buildsand evaluating different game design decisions pre-release. The ML-AgentsToolkit is mutually beneficial for both game developers and AI researchers as itprovides a central platform where advances in AI can be evaluated on Unity’srich environments and then made accessible to the wider research and gamedeveloper communities.

• 17+example Unity environments
• Support for multiple environment configurations and training scenarios
• Flexible Unity SDK that can be integrated into your game or custom Unity scene
• Support for training single-agent, multi-agent cooperative, and multi-agentcompetitive scenarios via several Deep Reinforcement Learning algorithms (PPO, SAC, MA-POCA, self-play).
• Support for learning from demonstrations through two Imitation Learning algorithms (BC and GAIL).
• Quickly and easily add your owncustom training algorithm and/or components.
• Easily definable Curriculum Learning scenarios for complex tasks
• Train robust agents using environment randomization
• Flexible agent control with On Demand Decision Making
• Train using multiple concurrent Unity environment instances
• Utilizes theSentis toprovide native cross-platform support
• Unity environmentcontrol from Python
• Wrap Unity learning environments as agym environment
• Wrap Unity learning environments as aPettingZoo environment

See ourML-Agents Overview page for detaileddescriptions of all these features. Or go straight to ourweb docs.

Our latest, stable release isRelease 22. Clickhereto get started with the latest release of ML-Agents.

You can also check out our newweb docs!

The table below lists all our releases, including ourmain branch which isunder active development and may be unstable. A few helpful guidelines:

• TheVersioning page overviews how we manage our GitHubreleases and the versioning process for each of the ML-Agents components.
• TheReleases pagecontains details of the changes between releases.
• TheMigration page contains details on how to upgradefrom earlier releases of the ML-Agents Toolkit.
• TheDocumentation links in the table below include installation and usageinstructions specific to each release. Remember to always use thedocumentation that corresponds to the release version you're using.
• Thecom.unity.ml-agents package isverifiedfor Unity 2020.1 and later. Verified packages releases are numbered 1.0.x.

If you are a researcher interested in a discussion of Unity as an AI platform,see a pre-print of ourreference paper on Unity and the ML-Agents Toolkit.

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

@article{juliani2020,  title={Unity: A general platform for intelligent agents},  author={Juliani, Arthur and Berges, Vincent-Pierre and Teng, Ervin and Cohen, Andrew and Harper, Jonathan and Elion, Chris and Goy, Chris and Gao, Yuan and Henry, Hunter and Mattar, Marwan and Lange, Danny},  journal={arXiv preprint arXiv:1809.02627},  url={https://arxiv.org/pdf/1809.02627.pdf},  year={2020}}

Additionally, if you use the MA-POCA trainer in your research, we ask that youcite the following paper as a reference:

@article{cohen2022,  title={On the Use and Misuse of Absorbing States in Multi-agent Reinforcement Learning},  author={Cohen, Andrew and Teng, Ervin and Berges, Vincent-Pierre and Dong, Ruo-Ping and Henry, Hunter and Mattar, Marwan and Zook, Alexander and Ganguly, Sujoy},  journal={RL in Games Workshop AAAI 2022},  url={http://aaai-rlg.mlanctot.info/papers/AAAI22-RLG_paper_32.pdf},  year={2022}}

We have a Unity Learn course,ML-Agents: Hummingbirds,that provides a gentle introduction to Unity and the ML-Agents Toolkit.

We've also partnered withCodeMonkeyUnity to create aseries of tutorial videoson how to implement and use the ML-Agents Toolkit.

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

• (July 12, 2021)ML-Agents plays Dodgeball
• (May 5, 2021)ML-Agents v2.0 release: Now supports training complex cooperative behaviors
• (December 28, 2020)Happy holidays from the Unity ML-Agents team!
• (November 20, 2020)How Eidos-Montréal created Grid Sensors to improve observations for training agents
• (November 11, 2020)2020 AI@Unity interns shoutout
• (May 12, 2020)Announcing ML-Agents Unity Package v1.0!
• (February 28, 2020)Training intelligent adversaries using self-play with ML-Agents
• (November 11, 2019)Training your agents 7 times faster with ML-Agents
• (October 21, 2019)The AI@Unity interns help shape the world
• (April 15, 2019)Unity ML-Agents Toolkit v0.8: Faster training on real games
• (March 1, 2019)Unity ML-Agents Toolkit v0.7: A leap towards cross-platform inference
• (December 17, 2018)ML-Agents Toolkit v0.6: Improved usability of Brains and Imitation Learning
• (October 2, 2018)Puppo, The Corgi: Cuteness Overload with the Unity ML-Agents Toolkit
• (September 11, 2018)ML-Agents Toolkit v0.5, new resources for AI researchers available now
• (June 26, 2018)Solving sparse-reward tasks with Curiosity
• (June 19, 2018)Unity ML-Agents Toolkit v0.4 and Udacity Deep Reinforcement Learning Nanodegree
• (May 24, 2018)Imitation Learning in Unity: The Workflow
• (March 15, 2018)ML-Agents Toolkit v0.3 Beta released: Imitation Learning, feedback-driven features, and more
• (December 11, 2017)Using Machine Learning Agents in a real game: a beginner’s guide
• (December 8, 2017)Introducing ML-Agents Toolkit v0.2: Curriculum Learning, new environments, and more
• (September 19, 2017)Introducing: Unity Machine Learning Agents Toolkit
• Overviewing reinforcement learning concepts(multi-armed banditandQ-learning)

• Unity Sentis
• Introducing Unity Muse and Sentis

The ML-Agents Toolkit is an open-source project and we encourage and welcomecontributions. If you wish to contribute, be sure to review ourcontribution guidelines andcode of conduct.

For problems with the installation and setup of the ML-Agents Toolkit, ordiscussions about how to best setup or train your agents, please create a newthread on theUnity ML-Agents forum and makesure to include as much detail as possible. If you run into any other problemsusing the ML-Agents Toolkit or have a specific feature request, pleasesubmit a GitHub issue.

Please tell us which samples you would like to see shipped with the ML-Agents Unitypackage by replying tothis forum thread.

Your opinion matters a great deal to us. Only by hearing your thoughts on theUnity ML-Agents Toolkit can we continue to improve and grow. Please take a fewminutes tolet us know about it.

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

In order to improve the developer experience for Unity ML-Agents Toolkit, we have added in-editor analytics.Please refer to "Information that is passively collected by Unity" in theUnity Privacy Policy.