We are excited to announce Gymnasium v1.0, the centerpiece of Farama, which our amazing volunteers have been working on for the last 3 years! To find out all the changes we made and why, read our release notes at github.com/Farama-Foundation…
Over that time, we have steadily improved the library- fixing bugs, adding new features and API changes where we believed necessary. With v1.0, the core API will not longer be changed. We’re excited to see what cool projects and agents users will create with Gymnasium v1.0!
3
460
☁️ Custom remotes: Now supporting Google Cloud Storage for hosting your own dataset collections
… and much more!
1
1
303
Get started now and learn more in our docs! 🔗 minari.farama.org
1
274
We are excited to announce MOMAland - the first multi-objective multi-agent RL library! In this setting, each agent learns policies while balancing multiple (conflicting) objectives.
Paper: arxiv.org/abs/2407.16312
Code: github.com/Farama-Foundation…
This library also brings open challenges. In cooperative settings with unknown preferences among objectives, solutions resemble those in single-agent MORL. In general settings with known preferences, solutions align with single-objective MARL.
1
323
However, in general settings with unknown preferences, we do not really know yet! Excited to try it out? You can install MOMAland with a simple “pip install momaland”.
Check out the documentation page for more information: momaland.farama.org/
1
299
Have you ever wondered why gym's "done" was replaced with "terminated" and "truncated"? Check out our new blog post, offering a deep dive into the motivation behind this change, alternatives considered, and its relation to RL theory: farama.org/Gymnasium-Termina…
We are excited to announce that ChatArena has joined the Farama Foundation! ChatArena is a library that provides multi-agent language game environments and facilitates research about autonomous LLM agents and their social interactions.
github.com/Farama-Foundation…
This is part of a broader initiative in supporting interdisciplinary research on RL and LLMs. ChatArena allows LLMs to interact with multi-agent PettingZoo environments such as Chess, and its own language-specific environments can be wrapped with PettingZoo to support RL agents.
1
2
330
Many thanks to @YuxiangJWu, @zhengyaojiang, and all other maintainers and contributors. If you are interested in contributing to the project, please reach out via our discord: discord.gg/9x375BdR
5
290
PettingZoo 1.24.0 is now live! This release includes Python 3.11 support, updated Chess and Hanabi environment versions, and many bugfixes, documentation updates and testing expansions. We are very excited to announce 3 tutorials using Stable-Baselines3.
github.com/Farama-Foundation…
Apologies for the broken link, here is a working release notes link:
github.com/Farama-Foundation…
3
281
We are releasing MiniWoB++ v1.0, an RL benchmark with over 100 web interaction environments from button clicks to complex web apps, with multimodal states and diverse actions. RL agents can interact with the browser via Selenium through the Gymnasium API.
github.com/Farama-Foundation…
New features from original MiniWoB++:
* Python 3 + Gymnasium API + Documentation
* More actions: drag, scroll, key combos + customization
* Fixed bugs in many environments + seed-determinism
* Added 18 hidden “test set” environments
Documentation website: miniwob.farama.org/
1
299

