Arcade-Learning-Environment VS stable-baselines3

This includes single-agent Gymnasium wrappers for DM Control, DM Lab, Behavior Suite, Arcade Learning Environment, OpenAI Gym V21 & V26. Multi-agent PettingZoo wrappers support DM Control Soccer, OpenSpiel and Melting Pot. For more information, read the release notes here:

They are talking about this: https://github.com/mgbellemare/Arcade-Learning-Environment

The code for Atari envs is not on gym, but on ALE

If you're more interested in playing games directly from pixel-level input, check out the Arcade Learning Environment, which lets you do this with all the old Atari games. You can find lots of tutorials online about using "reinforcement learning" to play these games.

I glanced over everything in this post, for a more detailed explainer check out the following blog post: https://brosa.ca/blog/ale-release-v0.7 and the release notes at https://github.com/mgbellemare/Arcade-Learning-Environment/releases/tag/v0.7.0.

I'm running some experiments on Atari via gym and have noticed that the MD5 checksums on around half of the ROMs supplied by gym[atari] differ from the MD5s listed here. Has anyone noticed this before, and would it make a difference to the results?

The latest release (v3.0.0) of Upkie's software brings a functional sim-to-real reinforcement learning pipeline based on Stable Baselines3, with standard sim-to-real tricks. The pipeline trains on the Gymnasium environments distributed in upkie.envs (setup: pip install upkie) and is implemented in the PPO balancer. Here is a policy running on an Upkie:

PettingZoo 1.24.0 is now live! This release includes Python 3.11 support, updated Chess and Hanabi environment versions, and many bugfixes, documentation updates and testing expansions. We are also very excited to announce 3 tutorials using Stable-Baselines3, and a full training script using CleanRL with TensorBoard and WandB.

I am wondering why there is so few algorithms in Stable Baselines 3 (SB3, https://github.com/DLR-RM/stable-baselines3/tree/master)? I was expecting some algorithms like ICM, HIRO, DIAYN, ... Why there is no model-based, skill-chaining, hierarchical-RL, ... algorithms implemented there?

Discord is more focused, and they have a page for people who wants to contribute https://github.com/DLR-RM/stable-baselines3/blob/master/CONTRIBUTING.md

Therefore, I debugged this error to the ReplayBuffer that was imported from `SB3`. This is the problem function -

Have you ever wanted to use dm-control with stable-baselines3? Within Reinforcement learning (RL), a number of APIs are used to implement environments, with limited ability to convert between them. This makes training agents across different APIs highly difficult, and has resulted in a fractured ecosystem.

Changelog: https://github.com/DLR-RM/stable-baselines3/releases/tag/v1.8.0

Great project! One question though, is there any reason why you are not using existing RL models instead of creating your own, such as stable baselines?