View Code? Open in Web Editor
NEW
This project forked from google-deepmind/bsuite
bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent
License: Apache License 2.0
Python 54.62%
Jupyter Notebook 14.50%
TeX 30.58%
Shell 0.30%
bsuite's Introduction
- ๐ Hi, Iโm @johan-kallstrom
- ๐ Iโm interested in reinforcement learning in multi-agent systems.
- ๐ฑ Iโm currently focused on multi-objective reinforcement learning in systems where human and synthetic agents must collaborate to solve tasks.
bsuite's People
Watchers