brax
pybullet-gym
Our great sponsors
brax | pybullet-gym | |
---|---|---|
11 | 7 | |
2,058 | 810 | |
3.3% | - | |
5.2 | 0.0 | |
10 days ago | over 2 years ago | |
Jupyter Notebook | Python | |
Apache License 2.0 | 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.
brax
-
4000x Speedup in Reinforcement Learning with Jax
There is Brax with its Ant, Humanoid and other rigid body articulated Gym environments: https://github.com/google/brax
- Physic engine for 3D simulation: which one to use?
-
Brax vs TDS for differentiable rigid body dynamics
I need differentiable rigid body dynamics because I want to do nonlinear MPC. One library that can do this is C++ is Tiny Differentiable Simulator https://github.com/erwincoumans/tiny-differentiable-simulator. As I understand it, this software uses a C++ auto-diff library and code generation to create CUDA kernels to compute fast derivatives in parallel. This seems pretty fast because it's C++. Another option is Brax https://github.com/google/brax. Brax uses JAX which I've never used, but from what I've seen online, JAX is popular for researchers and probably very good.
-
Deep learning for robotics
I am doing a MSc on robotics with a focus on machine learning, especially attention based architectures. There is a lot simulation and reinforcement learning going on. I have a funding of ~2500$ for the hardware system (no flexibility here, cannot use it for cloud either). I used pcpartpicker.com to select compatible components, as shown below. I am not located in the western part of the world; which means I have difficulty accessing some components and prices are higher here than that of pcpartpicker.com. That is why I am aiming towards 2000 - 2200$ range in the pcpartpicker.com. - Overall, what do you think of my planned setup? - Since there is a lot of simulation planned including rigid body dynamics with contact (libraries like https://github.com/raisimTech/raisimLib, https://github.com/deepmind/mujoco), I need some powerful CPU to use these libraries. I know that Intel has MKL over AMD; however, I am not sure how relevant that is for my case. The robotics simulators are generally written with C++, uses Eigen or their own math libraries. I feel like there is a lot of linear algebra involved and Intel combined with MKL should give me less headache. I have chosen i9-12900K, but what about AMD Ryzen9 5950X for example? - There is a new generation of rigid body simulators which use GPU instead of CPU (https://github.com/google/brax, https://developer.nvidia.com/isaac-gym). I do not think they are as mature as the previously mentioned simulators. Perhaps I am mistaken. Shall I focus on them instead? In terms of hardware that means I can downgrade the CPU to Ryzen5, and upgrade to RTX3080, roughly. - Do you think this system is easy to upgrade in future? What can I change to make it easier for long-term use and upgrades? Thanks for any help!
-
[D] Advice on Hardware Setup for Robotics
There is a new generation of rigid body simulators which use GPU instead of CPU (https://github.com/google/brax, https://developer.nvidia.com/isaac-gym). I do not think they are as mature as the previously mentioned simulators. Perhaps I am mistaken. Shall I focus on them instead? In terms of hardware that means I can downgrade the CPU to Ryzen5, and upgrade to RTX3080, roughly.
-
DeepMind open-sourcing MuJoCo simulator
I wonder what this means for the future of Brax [1].
1. https://github.com/google/brax
-
Any tutorial on how to create RL C++ environments?
If you want raw speed, parallel execution on GPU or TPU is best. Checkout out our Brax simulator, which uses the XLA compiler and JAX Python frontend: https://github.com/google/brax
-
Best environment to train RL agents
Check out Brax, hardware accelerated RL training in a Google Jupyter Colab. It trains typical RL tasks in minutes on TPU, also on GPU or CPU. And it is free, you can train with just a browser: https://github.com/google/brax
-
[N] Mujoco is free for everyone until October 31 2021
Anyone made any progress with Brax? That was sold as a massively-parallel Mujoco alternative but not sure if anyone's actually using it yet.
- [R] Brax: A Differentiable Physics Engine for Large Scale Rigid Body Simulation, with a focus on performance and parallelism on accelerators, written in JAX.
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?
mujoco - Multi-Joint dynamics with Contact. A general purpose physics simulator.
gym-pybullet-drones - PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control
tiny-differentiable-simulator - Tiny Differentiable Simulator is a header-only C++ and CUDA physics library for reinforcement learning and robotics with zero dependencies.
Super-mario-bros-PPO-pytorch - Proximal Policy Optimization (PPO) algorithm for Super Mario Bros
jax - Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
gym_solo - A custom open ai gym environment for solo experimentation.
RustyNEAT - Rust implementation of NEAT algorithm (HyperNEAT + ES-HyperNEAT + NoveltySearch + CTRNN + L-systems)
rl-baselines-zoo - A collection of 100+ pre-trained RL agents using Stable Baselines, training and hyperparameter optimization included.
open_spiel - OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
rex-gym - OpenAI Gym environments for an open-source quadruped robot (SpotMicro)
Numba - NumPy aware dynamic Python compiler using LLVM
rl-baselines3-zoo - A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.