on-policy
auto-sklearn
Our great sponsors
| on-policy | auto-sklearn | |
|---|---|---|
| 12 | 3 | |
| 1,125 | 7,403 | |
| 7.8% | 0.8% | |
| 4.9 | 1.8 | |
| 10 days ago | 4 months ago | |
| Python | Python | |
| MIT License | BSD 3-clause "New" or "Revised" License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
on-policy
- How do you compute rewards when you are using parallel environments?
-
Renderer of the environment does not work?
I am trying to feed the agents with visual observation and thus using the renderer of this environment (https://github.com/marlbenchmark/on-policy/blob/main/onpolicy/envs/mpe/rendering.py), but I get this as an image:
- Stuck on this error for days: I can't use importlib the right way
- Difference between setup.py, environments.yaml and requirements.txt
-
Ubuntu terminal crashes when I launch a deep reinforcement learning model
I am trying to run this code on my Ubuntu machine (https://github.com/marlbenchmark/on-policy).
-
"chmod" is not recognized as an internal or external command, operable program or batch file
If you don't want to install a Linux VM, the other option is to read the source of the train_mpe.sh script and write your own version as a Windows batch file.
-
Confused between "centralized critic" and "centralized training decentralized execution"
Sorry, this was the paper: https://arxiv.org/abs/2104.07750 But I guess you already answered my question. Indeed, agents receive a global obervation, but cannot directly observe other agents' actions, states, orrewards, and do not share parameters. So if I understand correctly that what they're using here is independent PPO with global observation, but no centralized critic. Which is what MAPPO (https://github.com/marlbenchmark/on-policy/blob/main/onpolicy/algorithms/r_mappo/algorithm/r_actor_critic.py) does: centralized observation space, but (if I'm correct), decentralized critic.
-
Why is this implementation of PPO using a replay buffer?
I don't see the buffer being cleared anywhere, but it looks to me like it may not need to... For example, the implementation of SeparatedReplayBuffer receives the episode_length (or "horizon" as is sometimes called) and sets the size of the buffer accordingly when its initialized. That way, the amount of samples collected before each policy/value update is constant. You just need one giant tensor block to collect all your samples, then after doing a networks update, why clear them out? Just overwrite the existing samples, since you know you'll collect exactly the same number of new samples.
-
MARL top conference papers are ridiculous
https://github.com/marlbenchmark/on-policy (MAPPO-FP)
auto-sklearn
-
Why not AutoML every tabular data?
Efficiency Ignoring the feature engineering aspects aside, a typical data scientist workflow involves trying out the different models. Some of the AutoML modules like H2O AutoML, AutoSklearn does this for you, and allow you to interpret your models. All these save so much time experimenting with the standard models.
- [R] Regularization is all you Need: Simple Neural Nets can Excel on Tabular Data
-
What free AutoML library do you recommend?
If you want a more stable AutoML library, i’ll suggest auto-sklearn which optimises performance of sklearn learning algorithms.
What are some alternatives?
gym-pybullet-drones - PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control
autogluon - AutoGluon: Fast and Accurate ML in 3 Lines of Code
DI-engine - OpenDILab Decision AI Engine
Auto-PyTorch - Automatic architecture search and hyperparameter optimization for PyTorch
tune-sklearn - A drop-in replacement for Scikit-Learn’s GridSearchCV / RandomizedSearchCV -- but with cutting edge hyperparameter tuning techniques.
syne-tune - Large scale and asynchronous Hyperparameter and Architecture Optimization at your fingertips.
OCTIS - OCTIS: Comparing Topic Models is Simple! A python package to optimize and evaluate topic models (accepted at EACL2021 demo track)
nni - An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.
SMAC3 - SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization
pymarl2 - Fine-tuned MARL algorithms on SMAC (100% win rates on most scenarios)
iterative-stratification - scikit-learn cross validators for iterative stratification of multilabel data
DIgging - Decision Intelligence for digging best parameters in target environment.