Max van Dijck 232c331ce3 [RLlib] Rename all np.product usage to np.prod (#46317) 3 月之前
..
examples 0e41f893a5 [RLlib-contrib] ddpg (#36259) 1 年之前
src 232c331ce3 [RLlib] Rename all np.product usage to np.prod (#46317) 3 月之前
tests 0e41f893a5 [RLlib-contrib] ddpg (#36259) 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
pyproject.toml 0e41f893a5 [RLlib-contrib] ddpg (#36259) 1 年之前
readme.md 0e41f893a5 [RLlib-contrib] ddpg (#36259) 1 年之前
requirements.txt 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

DDPG (Deep Deterministic Policy Gradient)

DDPG is an actor-critic, model-free algorithm based on the deterministic policy gradient that can operate over continuous action spaces.

Installation

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

Usage

DDPG Example