maze
dm_env
Our great sponsors
| maze | dm_env | |
|---|---|---|
| 4 | 2 | |
| 257 | 329 | |
| 1.2% | 3.3% | |
| 0.0 | 0.0 | |
| 22 days ago | over 1 year ago | |
| Python | Python | |
| GNU General Public License v3.0 or later | 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.
maze
-
[P] Maze: A Framework for Applied Reinforcement Learning
Check out Maze on GitHub - we'd love feedback from anybody with an interest and/or experience in reinforcement learning!
-
Maze: A Framework for Applied Reinforcement Learning
Check out Maze on GitHub and its documentation here.
-
Is there a consensus about RL frameworks?
For industrial and logistics problems this one looks promising: https://github.com/enlite-ai/maze saw their presentation 2 weeks ago at an international AI conference and was surprised that its already in use and available on github.
- MazeRL - Applied Reinforcement Learning with Python
dm_env
-
Worthwhile to convert custom env to be dm_env compatible?
Can anyone speak to their experience using acme (https://github.com/deepmind/acme) and by extension dm_env (https://github.com/deepmind/dm_env)? I'm wondering if it would be worthwhile for me to invest the time into converting my custom environment (which loosely follows the standard RL setup) over to this format.
-
[D] What would a "Production" RL stack look like in terms of tooling?
An interface based loosely on the standard RL setup. I'm thinking about adapting it to fit dm_env (https://github.com/deepmind/dm_env) to let it do more heavy lifting since I quite like Haiku, rlax and the rest of what they do.
What are some alternatives?
dcss-ai-wrapper - An API for Dungeon Crawl Stone Soup for Artificial Intelligence research.
panda-gym - Set of robotic environments based on PyBullet physics engine and gymnasium.
machin - Reinforcement learning library(framework) designed for PyTorch, implements DQN, DDPG, A2C, PPO, SAC, MADDPG, A3C, APEX, IMPALA ...
acme - A library of reinforcement learning components and agents
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)
nle - The NetHack Learning Environment
machine_learning_examples - A collection of machine learning examples and tutorials.
Ray - Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
RL-Adventure - Pytorch Implementation of DQN / DDQN / Prioritized replay/ noisy networks/ distributional values/ Rainbow/ hierarchical RL
multirotor - Multicopter UAV simulation for control/RL experiments.
lumos - Code and data for "Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs"