wanboo's repositories
awesome-reinforcement-learning
Learning Resources And Links Of Reinforcement Learning （updating）
MIT000
DDPG-for-process-optimization-
还在整理中..尝试将强化学习（DDPG框架）用于锌冶炼净化过程的锌粉添加量优化.。首先在matlab中搭建净化过程模型（agent)，然后通过python接口与主程序连接；然后搭建三层行动网络和评价网络；基于梯度下降算法训练网络参数。整个训练过程发散，而且无法解决。可能原因在于过程模型复杂，在只有有限数据条件下很难用神经网络逼近，从而造成无法收敛。代码基于tensorflow，python和matlab。
000
FlexibleJobShopDynamicScheduling
flexible job shop static and dynamic scheduling based on SPT dispatch rules
MIT000
ReinforcementLearning_experiment
最近在做一些强化学习方面的工作，这里对一些传统的强化学习算法做一个总结，不断整理
000
RL_for_dynamic_scheduling
Implementation of the paper "A Reinforcement Learning Based Strategy for Dynamic Scheduling on Heterogeneous Platforms".
000
scheduling
static scheduling with branch and bound; dynamic scheduling with RL.
000