Comments (3)
Hi, thank you for your suggestion.
Currently, we do not have any plans to update Ray and Gym for two reasons.
First, Ray and RLlib are not backward compatible, which means updating them could potentially cause issues with existing code and workflows.
Second, the environment integrated into MARLlib is not compatible with the latest version of Gymnasium, which would require significant changes and updates to ensure compatibility.
Therefore, for now, we have decided to hold off on updating Ray and Gym until these compatibility issues can be addressed and resolved.
from marllib.
Just for what it's worth, if you need help in updating to Gymnasium and current PettingZoo I can offer some help, the main difference is just changing from done
to termination
and truncation
, as explained in the migration guide. I understand the idea of wanting things to be fully backwards compatible, but all major training libraries (RLlib, Stable-Baselines3, Tianshou, CleanRL) are working with current versions of PettingZoo and Gymnasium. Using unmaintained software is never desirable, and the easiest way to ensure everything is reproducible and consistent between libraries is to just use the current versions.
As you show in the README there are already 5+ different libraries trying to standardize MARL training and benchmarks, but most are not actively maintained, given that your project is maintained actively it seems like it would make a lot of sense to be using the most recent versions.
I just finished a tutorial for Stable-Baselines3 on PettingZoo and was thinking I would love to add some other MARL-specific libraries to our official tutorials, I think it would be a really useful asset to be able to point users to your library, if it weren't using 2+ year old versions of the PettingZoo/still using unmaintained Gym.
from marllib.
I have been using Gymnasium as it has also been adopted in Ray 2.x.
I agree that change is simple.
I would like to upgrade the MARL policies to Ray 2.5, but I noticed Ray 3.x, which is still dev, has breaking changes, so I will wait till 3.0 release.
from marllib.
Related Issues (20)
- Doing Counterfactual Experience Replay HOT 9
- JointQ not work in custom env HOT 1
- Trouble implementing custom environment HOT 3
- Episodes_this_iter parameter
- Supporting Individual Action Spaces
- How to export trained model as a .pt (pytorch ) or ONNX model. HOT 2
- How do I get an agent's position in the environment in the `postprocess_trajectory` method? HOT 1
- IQL setup for Custom Env
- Can the qmix algorithm solve the AirCombat problem and does Marllib support it?
- Training agents with IQL HOT 3
- Query Regarding num_workers Setting Resulting in Multiple Concurrent Environments During Training
- Inferencing the learned Policies HOT 2
- Inter-agent communication before compute_actions HOT 1
- How to set up exploration strategies for Agents?
- Confusing results in simple spread environment HOT 1
- Zero reward in Overcooked environment regardless of algorithm/length of training
- NaN rewards in custom environment HOT 2
- how to fine tune pre-trained policies for new env ?
- Outdated ray requirement (ray=1.8.0) HOT 1
- metadrive agent policy mapping: agent_n more than assigned number of agents
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from marllib.