machin
RL-Adventure
Our great sponsors
machin | RL-Adventure | |
---|---|---|
2 | 3 | |
381 | 2,903 | |
- | - | |
1.8 | 0.0 | |
over 2 years ago | over 2 years ago | |
Python | Jupyter Notebook | |
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.
machin
-
Best PyTorch RL library for doing research
Machin is really nice, it is very easy to use and to try different things, although it’s developed by one person and maybe not appropriately tested yet.
-
Is there a consensus about RL frameworks?
I found this repo very helpful to get started: https://github.com/iffiX/machin
RL-Adventure
-
Applied resources in Pytorch?
can check this out.
-
Is there a consensus about RL frameworks?
For me, nothing beats RL-Adventure. It's not perfect, it has bugs, but it's super readable and will let you level up through the different main methods.
-
[N] 20 hours of new lectures on Deep Learning and Reinforcement Learning with lots of examples
Lecture 7: Function approximation. (slides, code, video)
What are some alternatives?
stable-baselines3 - PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
cleanrl - High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
dcss-ai-wrapper - An API for Dungeon Crawl Stone Soup for Artificial Intelligence research.
Apache Impala - Apache Impala
nle - The NetHack Learning Environment
tianshou - An elegant PyTorch deep reinforcement learning library.
RL-Adventure-2 - Fault-tolerant, highly scalable GPU orchestration, and a machine learning framework designed for training models with billions to trillions of parameters [Moved to: https://github.com/higgsfield-ai/higgsfield]
ElegantRL - Massively Parallel Deep Reinforcement Learning. 🔥
flux-beamer - Flux is a modern style beamer presentation.
seed_rl - SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's architecture.
acme - A library of reinforcement learning components and agents