Is there a consensus about RL frameworks?

• machin

  2 381 1.8 Python

  Reinforcement learning library(framework) designed for PyTorch, implements DQN, DDPG, A2C, PPO, SAC, MADDPG, A3C, APEX, IMPALA ...

I found this repo very helpful to get started: https://github.com/iffiX/machin

• maze

  4 257 0.0 Python

  Maze Applied Reinforcement Learning Framework

  

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.

• InfluxDB

  www.influxdata.com sponsored

  Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

  

• RL-Adventure

  3 2,903 0.0 Jupyter Notebook

  Pytorch Implementation of DQN / DDQN / Prioritized replay/ noisy networks/ distributional values/ Rainbow/ hierarchical RL

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.

• nle

  15 933 3.7 C

  The NetHack Learning Environment

  

Nethack Repo https://github.com/facebookresearch/nle

• dcss-ai-wrapper

  5 38 3.7 Python

  An API for Dungeon Crawl Stone Soup for Artificial Intelligence research.

DCSS AI Wrapper GitHub (under heavy development at the moment) https://github.com/dtdannen/dcss-ai-wrapper

• stable-baselines3

  46 7,894 8.2 Python

  PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

  

Suggest a related project