代码
注册 登录
简体中文
简体中文 English
openoker
/
ray
1
0
收藏 0
文件 工单管理 0 Wiki
分支: master
分支列表 标签列表
Max van Dijck 232c331ce3 [RLlib] Rename all np.product usage to np.prod (#46317) 3 月之前
..
examples 71965c421d [RLlib-contrib] PG. (#36666) 1 年之前
src 71965c421d [RLlib-contrib] PG. (#36666) 1 年之前
tests 71965c421d [RLlib-contrib] PG. (#36666) 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 71965c421d [RLlib-contrib] PG. (#36666) 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

PG (Vanilla Policy Gradient)

PG is the most basic reinforcement learning algorithm that learns a policy by taking a gradient of action log probabilities and weighting them by the return. This algorithm is also known as REINFORCE.

Installation

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

Usage

[PG Example]()