Max van Dijck 232c331ce3 [RLlib] Rename all np.product usage to np.prod (#46317) 3 月之前
..
examples 3b56729de9 [RLlib-contrib] ARS. (#36607) 1 年之前
src 3b56729de9 [RLlib-contrib] ARS. (#36607) 1 年之前
tests 3b56729de9 [RLlib-contrib] ARS. (#36607) 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 3b56729de9 [RLlib-contrib] ARS. (#36607) 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

README.md

ARS (Asynchronous Advantage Actor-Critic)

ARS ARS is a random search method for training linear policies for continuous control problems. Code here is adapted from https://github.com/modestyachts/ARS to integrate with RLlib APIs.

Installation

conda create -n rllib-ars python=3.10
conda activate rllib-ars
pip install -r requirements.txt
pip install -e '.[development]'

Usage

[ARS Example]()