jaxrl
sbx
| jaxrl | sbx | |
|---|---|---|
| 2 | 5 | |
| 576 | 265 | |
| - | - | |
| 0.0 | 6.6 | |
| over 1 year ago | 23 days ago | |
| Jupyter Notebook | Python | |
| MIT License | MIT 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.
jaxrl
-
JAX in Reinforcement Learning
Have you looked at this repo or this repo ?
-
CleanRL now has a DDPG + JAX implementation roughly 2.5-4x faster than DDPG + PyTorch
https://github.com/ikostrikov/jaxrl would be another great reference implementation. Probably you want to also checkout the docs for jax, flax, and optax.
sbx
-
Stable-Baselines3 v2.0: Gymnasium Support
Stable-Baselines Jax (SBX): https://github.com/araffin/sbx
-
JAX in Reinforcement Learning
If you want to learn from examples, you can take a look at clean rl or stable baselines jax (sbx): https://github.com/araffin/sbx
-
How can I speed up SAC?
You mean wallclock time or sample efficiency? For the former, you can take a look at Jax implementation like: https://github.com/araffin/sbx (SB3 + Jax)
-
Stable-Baselines3 v1.8 Release
The Hindsight Experience Replay (HER) buffer is compatible with all off-policy reinforcement learning algorithms. (and also compatible with the Jax version of SB3: https://github.com/araffin/sbx/pull/11).
-
JAX or PyTorch?
I haven't used JAX yet but quite excited about it - Little plug for SBX https://github.com/araffin/sbx which seems quite clean!
What are some alternatives?
jaxrl_m - Skeleton for scalable and flexible Jax RL implementations
stable-baselines3 - PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
indaba-pracs-2022 - Notebooks for the Practicals at the Deep Learning Indaba 2022.
cleanrl - High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
fselect - Find files with SQL-like queries
Popular-RL-Algorithms - PyTorch implementation of Soft Actor-Critic (SAC), Twin Delayed DDPG (TD3), Actor-Critic (AC/A2C), Proximal Policy Optimization (PPO), QT-Opt, PointNet..
Study-Time-Tally - Track your study hours.
uvadlc_notebooks - Repository of Jupyter notebook tutorials for teaching the Deep Learning Course at the University of Amsterdam (MSc AI), Fall 2023
Terminal-Video-Player - A program that can display video in the terminal using ascii characters
RL-X - A framework for Reinforcement Learning research.
rl-baselines3-zoo - A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.