jonah791/dsh-experience-policy ↗★ 0

dsh-experience-policy

经验策略:把「状态→动作→回报」的历史经验转成对当前候选动作的数值加权(JitRL 式 test-time policy optimization 的本地实现,零梯度) 本地实现零梯度的强化学习策略优化,适合需要动态调整决策权重的任务。

Package
dsh-experience-policy
Compatibility
Unverified
Harness peer range
>=0.1.0-rc.6
Cordis peer range
^4.0.1
Version
0.1.0
Last updated
Oct 15, 2026

Install

This plugin has no verified bundle, or compatibility checks failed. Read the repository notes first. Read the full README ↗

配置

项默认说明
(见源码 Config)—本插件无必填项;缺省即按纯决策层工作(经验数据由调用方持有并喂入)