Comments (5)
I thought about it while developing my code, but soon discovered it requires some time since the code structure for the newest RLlib has changed, which means 2 major changes (most of them boilerplate changes) to the codebase:
- a lot of imports need to be modified, such as the "agents" folder no longer exists, it is now "algorithm".
- All MARLlib trainers are based on a class construction method
build_trainer
, which has been discarded since ray 1.9 (see https://docs.ray.io/en/latest/rllib/package_ref/algorithm.html#building-custom-algorithm-classes) , so all trainers need to be rewritten.
Therefore, the update may heavily depend on the availability and time of developers, let us remain hopeful :)
from marllib.
Thank you for the answer. I was just thinking if there might be improvements in reliability and efficiency.
I installed MARLlib through pip install marllib
and manually installed ray and torch. BUT:
There is an error when trying to install the packages with the current specifications: pip installl ray==1.8.0
is not available as well as torch==1.9.0
. Updating this to the closest new version ray==1.13.0
and torch==1.11.0
does not even run the simple example code provided. Please help!
from marllib.
I understand your concern now. I remember installing the environment with torch==2.1.0
and ray==1.8.0
with no problem. (First the torch, then the ray). I downgraded from the latest ray to 1.8.0. Installation should also include ray[rllib]
and ray[tune]
.
I'm not sure why 1.8.0 is not available in your environment, since the versions I fetched from my environment have 1.8.0 presented:
(from versions: 1.4.1, 1.5.0, 1.5.1, 1.5.2, 1.6.0, 1.7.0rc0, 1.7.0, 1.8.0, 1.9.0rc1, 1.9.0rc2, 1.9.0, 1.9.1rc0, 1.9.1, 1.9.2, 1.10.0rc0, 1.10.0, 1.11.0rc0, 1.11.0rc1, 1.11.0, 1.11.1, 1.12.0rc1, 1.12.0, 1.12.1, 1.13.0, 2.0.0rc0, 2.0.0rc1, 2.0.0, 2.0.1, 2.1.0, 2.2.0, 2.3.0rc0, 2.3.0, 2.3.1, 2.4.0, 2.5.0, 2.5.1, 2.6.0, 2.6.1, 2.6.2, 2.6.3, 2.7.0rc0, 2.7.0, 2.7.1, 2.7.2, 2.8.0, 2.8.1, 2.9.0, 2.9.1, 2.9.2)
You can try changing the index source for the pip, which may resolve the problem.
Unfortunately I forgot the exact installation procedure, and further help may require some time to reproduce your situation.
from marllib.
i meet some bug on old version of RLlib when i extend new env on marllib, and new version of RLlib is also more intuitive,really hope they can update it
from marllib.
A makeshift solution is to copy the selected source code from the newest RLlib and put it in the "marllib/patch" directory, manually replacing the hard link from rllib with add_patch.py
or command line. It requires pip install -e .
though, which may create some inconvenience.
from marllib.
Related Issues (20)
- 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
- Does Marllib support dynamic environments?
- Does MARLlib support a mixed scenario where each agent has a different policy?
- When running the iddpg algorithm in the MAMujoco environment, the memory keeps increasing. HOT 1
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.