rl-baselines3-zoo
optuna
Our great sponsors
rl-baselines3-zoo | optuna | |
---|---|---|
11 | 32 | |
1,731 | 9,471 | |
4.5% | 3.0% | |
6.3 | 9.9 | |
17 days ago | 1 day ago | |
Python | Python | |
MIT License | GNU General Public License v3.0 or later |
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.
rl-baselines3-zoo
-
Stable-Baselines3 v2.0: Gymnasium Support
RL Zoo3 (training framework): https://github.com/DLR-RM/rl-baselines3-zoo
-
Simple continuous environment with spaceship but yet challenging for RL algorithms (like SAC, TD3)
Try hyperparameter search. It's implemented here: https://github.com/DLR-RM/rl-baselines3-zoo for stable-baselines3. Hyperparameters make a huge difference in RL, much more than in supervised learning.
-
Easily load and upload Stable-baselines3 models from the Hugging Face Hub 🤗
Integrating RL-baselines3-zoo
-
DDPG not solving MountainCarContinuous
- you can find tuned hyperparameters for DDPG, SAC, PPO in https://github.com/DLR-RM/rl-baselines3-zoo
-
Hyperparameter tuning examples
For more complete implementation: https://github.com/DLR-RM/rl-baselines3-zoo
-
How do I convert zoo / gym trained models to TensorFlow Lite or PyTorch TorchScript?
https://github.com/DLR-RM/rl-baselines3-zoo (PyTorch based, using https://github.com/DLR-RM/stable-baselines3)
-
[P] Stable-Baselines3 v1.0 - Reliable implementations of RL algorithms
We also release 100+ trained models in our experimental framework, the rl zoo: https://github.com/DLR-RM/rl-baselines3-zoo
-
JAX Implementations of Actor-Critic Algorithms
for pytorch, use the rl zoo (https://github.com/DLR-RM/rl-baselines3-zoo) and sb3 ;) https://github.com/DLR-RM/stable-baselines3
optuna
- How to test optimal parameters
-
How did you make that?!
The network configuration process is usually not particularly scientific and mostly relies on empirical observation. For some cases, tools like Optuna can be used to automatically find the optimal parameters. In others, on others, you can look for modern studies which explore the effect of this parameter on performance, such as this study (2022), but these are typically very specific to one particular architecture.
-
[P] We are building a curated list of open source tooling for data-centric AI workflows, looking for contributions.
Keras Tuner, Optuna : https://github.com/optuna/optuna ?
-
Suggestion to optimize algo
I have used OpenTuner, but I don't think it is maintained anymore. I hear tell that Optuna is what to use now, but have not used it myself. https://optuna.org Optuna - A hyperparameter optimization framework
-
[D]How to optimize an ANN?
You can use Optuna, SMAC or hyperopt
-
Optuna: An open source hyperparameter optimization framework to automate hyperparameter search
Optuna is a great library and I do use it in tuneta for optimizing technical indicator parameters. However, certain Optuna algos suggest the same parameters in separate trials resulting in many duplicate parameters (issue) which needs to be managed external of the lib.
-
The loss function of my model (Not a NN model) is not differentiable, what should I do?
if your parameter set is not too large, you could try black-box optimization via something like Optuna
- SPO600 project part 1
-
Trading Algos - 5 Key Metrics and How to Implement Them in Python
Nothing can beat iteration and rapid optimization. Try running things like grid experiments, batch optimizations, and parameter searches. Take a look at various packages like hyperopt or optuna as packages that might be able to help you here!
What are some alternatives?
Ray - Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
hyperopt - Distributed Asynchronous Hyperparameter Optimization in Python
nni - An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.
stable-baselines - A fork of OpenAI Baselines, implementations of reinforcement learning algorithms
stable-baselines3 - PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
mljar-supervised - Python package for AutoML on Tabular Data with Feature Engineering, Hyper-Parameters Tuning, Explanations and Automatic Documentation
pyGAM - [HELP REQUESTED] Generalized Additive Models in Python
gym-pybullet-drones - PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control
rl-baselines-zoo - A collection of 100+ pre-trained RL agents using Stable Baselines, training and hyperparameter optimization included.
pg_plan_advsr - PostgreSQL extension for automated execution plan tuning
pybullet-gym - Open-source implementations of OpenAI Gym MuJoCo environments for use with the OpenAI Gym Reinforcement Learning Research Platform.
SMAC3 - SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization