Reinforcement Learning Day 3 (Finite Markov Decision Processes)

• Return, Policy and Value Function
• Optimal Policies and Optimal Value Functions
• Coursera False Questions
• Optimality and Approximation
• Summary
  Read more »

最近又再捣鼓捣鼓自己HKKB的键盘，一直没有整明白自己的HHKB后面那一串开关的用处，后面写了一串英文介绍也没弄懂是怎么使用。经过仔细探究发现主要要的三个用途。

MetaLearning Learning Note - 2

Stanford CS330: Multi-Task and Meta-Learning, 2019 | Lecture 3 - Optimization-Based Meta-Learning

• Recap the probabilistic formulation of meta-learning
• general recipe of meta-learning algorithm
• black box adaption appraoches
• optimization-based meta-learning algorithm

Preface

I choose to learn meta-learning through the stanford’s coursework. Prof.Song and Dr.Xu ask me do some work around reinforcement learning and meta learning. Therefore, I choose to learn meta learning from stanford’s coursework by Chelsea Finn.

Reinforcement Learning Day 2 (Multi-armed Bandits)

• Q* Formula
• Nonstationary problem
• Optimistic Initial Value
• Gradient Bandits Problem
• Associative Search
  Read more »

Insights for co-run HPC AND GPU taks - Day5 Try some examples for co-run HPC and ML tasks

• Build the production environment
• NPB
  Read more »

Slurm Source Code Install | Cluster Deployment - Day4： Methods of Slurm to restrict resources

• Support for Multi-core/Multi-thread Architectures (srun to control resources usage)
• Consumable Resources in Slurm
• Resource Binding
• CPU Management User and Administrator Guide
• GRES
  Read more »

Slurm Source Code Install | Cluster Deployment - Day3 Deploy slurm

• Running it
• Cgroup Deployment
  Read more »