rl-baselines3-zoo
pybullet-gym
Our great sponsors
rl-baselines3-zoo | pybullet-gym | |
---|---|---|
11 | 7 | |
1,777 | 810 | |
5.0% | - | |
6.3 | 0.0 | |
27 days ago | over 2 years 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
-
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
pybullet-gym
-
Well, at least Epic kinda started "promoting" Rocket League inside Fortnite LUL
And when something like "RL/Fortnite Racing" comes out, with shared inventory, it may work as the pilot "beta test" of RL finally working in UE5. At least the game's physics engine (pybullet.org) is independent of the graphics. https://x.com/CactousMan/status/1690437803711320064
-
Mujoco vs Pybullet for closed loop chain environment
From what I know in pybullet you define the system of the environment loading an urdf file. So if you check the InvertedPendulum environment of pybullet I think you could create your desired urdf without a problem. I have not used mujoco, but it seems strange that it could not do what you want to do... Maybe there is a parameter of the joints or some kind of tolerance for the initial position?
-
Alternatives to Unity3D for simulating 3D environments with realistic physics for robotics and training a reinforcement learning model?
So far I found PyBullet, RobotPy, RobotDK, SOFA, and some others, but I wonder if there is something that is comparable or better than Unity 3D for this specific use case.
-
Getting started in 3D design
yeah, i guess compared to modeling tools like tinkercad, blender is not intuitive and hard to learn. im not aware of any FEM with blender but there's bullet, basis of https://pybullet.org/. blender has an omniverse connector now so it could probably be used in a pipeline with nvidia's isaac. https://developer.nvidia.com/isaac-sim https://developer.nvidia.com/blog/introducing-omniverse-usd-support-for-blender/
-
I’m 15 and this is yeet
Programming is also really important when learning anything about machine learning and I would start out with the OpenAI Gym and its derivative for learning some of the simpler algorithms on toy environments that doesn't require a whole lot of computing power. Then you can move on to the more hardware constrained simulators that I mentioned in the previous comment (MuJoCo, PyBullet, NVIDIA Isaac Gym).
-
[N] Mujoco is free for everyone until October 31 2021
shout-out to the open-source clones of the mujoco gym environments here
- Ask questions ahead of the Microsoft Research RL AMA on March 24 with John Langford and Akshay Krishnamurthy
What are some alternatives?
optuna - A hyperparameter optimization framework
brax - Massively parallel rigidbody physics simulation on accelerator hardware.
stable-baselines - A fork of OpenAI Baselines, implementations of reinforcement learning algorithms
gym-pybullet-drones - PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control
stable-baselines3 - PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
Super-mario-bros-PPO-pytorch - Proximal Policy Optimization (PPO) algorithm for Super Mario Bros
gym_solo - A custom open ai gym environment for solo experimentation.
rl-baselines-zoo - A collection of 100+ pre-trained RL agents using Stable Baselines, training and hyperparameter optimization included.
rl-trained-agents - A collection of pre-trained RL agents using Stable Baselines3
rex-gym - OpenAI Gym environments for an open-source quadruped robot (SpotMicro)