aimclub / aimclub/GOLEM

Research on Adaptive Mutations

未关闭
#40 0 条评论 0 个 reaction 已指派 0 人 在 GitHub 查看
adaptive priority 2023 research
主要语言
Python
星标
73
派生
11
平均合并
8 小时 51 分钟
30 天内合并 PR
4

描述

The idea is to adapt mutations during optimizations process, so that mutation probabilities would help in faster and better convergence.

Each mutation can be considered as *Action* in certain *State* (graph or node context) with certain *Reward*. This perspective opens several possibilities of multi-armed bandit formulation and RL formulation of adaptive mutations.

Subissues:
- [ ] #39
- [x] #41
- [x] #42
- [x] #77
- [ ] #43
- [ ] #98

Following is also useful:
- [x] #38
- [x] #83

贡献指南

这个仓库没有索引到贡献指南

评估

这个 Issue 还没有评估数据。

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。