Max van Dijck 232c331ce3 [RLlib] Rename all np.product usage to np.prod (#46317) | 3 月之前 | |
---|---|---|
.. | ||
examples | 5f25de5d48 [RLlib-contrib] QMIX. (#36682) | 1 年之前 |
src | 5f25de5d48 [RLlib-contrib] QMIX. (#36682) | 1 年之前 |
tests | 5f25de5d48 [RLlib-contrib] QMIX. (#36682) | 1 年之前 |
tuned_examples | a9ac55d4f2 [RLlib; RLlib contrib] Move `tuned_examples` into rllib_contrib and remove CI learning tests for contrib algos. (#40444) | 1 年之前 |
BUILD | a9ac55d4f2 [RLlib; RLlib contrib] Move `tuned_examples` into rllib_contrib and remove CI learning tests for contrib algos. (#40444) | 1 年之前 |
README.md | 5f25de5d48 [RLlib-contrib] QMIX. (#36682) | 1 年之前 |
pyproject.toml | 232c331ce3 [RLlib] Rename all np.product usage to np.prod (#46317) | 3 月之前 |
requirements.txt | 232c331ce3 [RLlib] Rename all np.product usage to np.prod (#46317) | 3 月之前 |
QMIX Q-Mix is a specialized multi-agent algorithm. Code here is adapted from https://github.com/oxwhirl/pymarl_alpha to integrate with RLlib multi-agent APIs. To use Q-Mix, you must specify an agent grouping in the environment (see the two-step game example). Currently, all agents in the group must be homogeneous. The algorithm can be scaled by increasing the number of workers or using Ape-X.
conda create -n rllib-qmix python=3.10
conda activate rllib-qmix
pip install -r requirements.txt
pip install -e '.[development]'
[QMIX Example]()