BDPI

Bootstrapped Dual Policy Iteration: sample-efficient model-free RL with discrete actions

Description:

Two BDPI implementations, both in Python with the OpenAI Gym. The vub-ai-lab one is 100% custom code, and has high-performance multiprocessing (able to leverage 32 cores or more). The sb3-contrib version is part of a well-known repository of RL algorithms with a common API (stable-baselines3), and is made to be very easy to try out by novice users.

More Information:

Originates from the Collaborative AI research challenge (FAIR 2019–2023).
Responsible Research Lead: Ann Nowé
Authors: Denis Steckelmacher
Programming Language: Python
Link to the repository: https://github.com/vub-ai-lab/bdpi and https://github.com/steckdenis/stable-baselines3-contrib