Rewrite Quickstart for Deep Reinforcement Learning as a Quickstart for stable-baselines3 users

rlberry-py / rlberry

An easy-to-use reinforcement learning library for research and education.

https://rlberry-py.github.io/rlberry

MIT License

160 stars 30 forks source link

Rewrite Quickstart for Deep Reinforcement Learning as a Quickstart for stable-baselines3 users #439

Closed KohlerHECTOR closed 2 weeks ago

KohlerHECTOR commented 3 months ago

Maybe we should change this quickstart to not use A2C from rlberry but use instead stable-baselines3 agent from expermient manager. A posteriori we could include @JulienT01 #395 work on fetching benchmarks from sb3 zoo in this quickstart. The core idea is to show how rlberry used in conjunction with stable-baselines3 can produce a full reproducible and fair comparisons research pipeline.