Max van Dijck 232c331ce3 [RLlib] Rename all np.product usage to np.prod (#46317) 3 月之前
..
examples 627023bf08 [rllib-contrib] add R2d2 to RLlib contrib (#36473) 1 年之前
src 627023bf08 [rllib-contrib] add R2d2 to RLlib contrib (#36473) 1 年之前
tests 627023bf08 [rllib-contrib] add R2d2 to RLlib contrib (#36473) 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 627023bf08 [rllib-contrib] add R2d2 to RLlib contrib (#36473) 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

R2D2 (Recurrent Experience Replay In Distributed Reinforcement Learning)

R2D2 is a version of DQN that is adapted to enable RNN based policies.

Installation

conda create -n rllib-r2d2 python=3.10
conda activate rllib-r2d2
pip install -r requirements.txt
pip install -e '.[development]'

Usage

[R2D2 Example]()