rl-baselines3-zoo
Ray
Our great sponsors
rl-baselines3-zoo | Ray | |
---|---|---|
11 | 42 | |
1,777 | 31,101 | |
5.0% | 3.1% | |
6.3 | 10.0 | |
26 days ago | about 1 hour ago | |
Python | Python | |
MIT License | Apache License 2.0 |
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
-
Can't solve MountainCar-v0 with A2C algorithm (stable-baselines3)
I'm trying to solve MountainCar-v0 enviroment from gymnasium with the A2C algorithm and the agent doesn't find a solution. I checked this so I added import stable_baselines3.common.sb2_compat.rmsprop_tf_like as RMSpropTFLike. Also checked the rl-baselines3-zoo for the hyperparameter tuning. So my code is:
-
Stable-Baselines3 v2.0: Gymnasium Support
RL Zoo3 (training framework): https://github.com/DLR-RM/rl-baselines3-zoo
-
Tips and Tricks for RL from Experimental Data using Stable Baselines3 Zoo
I'm still new to the domain but wanted to shared some experimental data I've gathered from massive amount of experimentation. I don't have a strong understanding of the theory as I'm more of a software engineer than data scientist, but perhaps this will help other implementers. These notes are based on Stable Baselines 3 and RL Baselines3 Zoo with using PPO+LSTM (should apply generally to all the algos for the most part)
-
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
-
Help comparing Double DQN against another paper's results
Hello, I've been running some tests of Double DQN with Stable Baselines 3 Zoo and to compare I'm using the graphs provided by Noisy Networks For Exploration.
-
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
Ray
-
Open Source Advent Fun Wraps Up!
22. Ray | Github | tutorial
-
Fine-Tuning Llama-2: A Comprehensive Case Study for Tailoring Custom Models
Training times for GSM8k are mentioned here: https://github.com/ray-project/ray/tree/master/doc/source/te...
- Ray – an open source project for scaling AI workloads
-
Methods to keep agents inside grid world.
Here's a reference from RLlib that points to docs and an example, and here's one from one of my projects that includes all my own implementations
-
TransformerXL + PPO Baseline + MemoryGym
RLlib
- Is dynamic action masking possible in Rllib?
-
AWS re:Invent 2022 Recap | Data & Analytics services
⦿ AWS Glue Data Quality - Automatic data quality rule recommendations based on your data AWS Glue for Ray - Data integration with Ray (ray.io), a popular new open-source compute framework that helps you scale Python workloads
-
Think about it for a second
https://ray.io (just dropping the link)
-
Elixir Livebook now as a desktop app
I've wondered whether it's easier to add data analyst stuff to Elixir that Python seems to have, or add features to Python that Erlang (and by extension Elixir) provides out of the box.
By what I can see, if you want multiprocessing on Python in an easier way (let's say running async), you have to use something like ray core[0], then if you want multiple machines you need redis(?). Elixir/Erlang supports this out of the box.
Explorer[1] is an interesting approach, where it uses Rust via Rustler (Elixir library to call Rust code) and uses Polars as its dataframe library. I think Rustler needs to be reworked for this usecase, as it can be slow to return data. I made initial improvements which drastically improves encoding (https://github.com/elixir-nx/explorer/pull/282 and https://github.com/elixir-nx/explorer/pull/286, tldr 20+ seconds down to 3).
[0] https://github.com/ray-project/ray
-
Learn various techniques to reduce data processing time by using multiprocessing, joblib, and tqdm concurrent
Adding these for anyone who had a similar question about Ray vs dask 1, 2, 3
What are some alternatives?
optuna - A hyperparameter optimization framework
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.
Faust - Python Stream Processing
gym-pybullet-drones - PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control
gevent - Coroutine-based concurrency library for Python
rl-baselines-zoo - A collection of 100+ pre-trained RL agents using Stable Baselines, training and hyperparameter optimization included.
pybullet-gym - Open-source implementations of OpenAI Gym MuJoCo environments for use with the OpenAI Gym Reinforcement Learning Research Platform.
SCOOP (Scalable COncurrent Operations in Python) - SCOOP (Scalable COncurrent Operations in Python)