笔记本
论文笔记
路径规划
1. Bezier curve & B-spline
2. Btraj论文笔记
3. Fast Planner论文笔记(1)
强化学习
1. Trust Region Policy Optimization
2. AC using K-FAC TR (ACKTR)
3. Proximal Policy Optimization
4. Deterministic Policy Gradient
5. Continuous Control with DRL
6. Twin Delayed DDPG (TD3)
7. Soft Actor-Critic
Robotics
《Principles of Robot Motion》
3. Configuration Space
4. Potential Functions
5. Roadmaps
Neural Radiance Fields, NeRF
1. NeRF初步
2. MLP与优化算法
3. NeRF开山之作
4. Mip-NeRF
《Optimal Control Systems》
1. Introduction
2. Calculus of Variations and Optimal Control
3. Linear Quadratic Optimal Control Systems 1
8. Appendix B
运筹学
《运筹学导论》
1. Introduction
2. OR建模方法综述
8. 运输和指派问题
线性规划
1. Preliminaries
2. Geometry of LP
3. Simplex Method
4. Duality & Sensitivity Analysis
整数规划
1. Branch-and-Bound Method
2. Totally Unimodularity and Network Flows
3. Dynamic Programming
4. Computational Complexity
机器学习
机器学习概论
1. 决策树
2. 贝叶斯学习
3. MM & HMM
深度学习
1. Introduction
1.2. General Guidance
1.3. Brief Talk on ML
2. What to Do If Training Fails
3. Image as Input
4. Sequence as Input
4.2. Graph Neural Networks
5. Seq2seq — Transformer
7. Self-Supervised Learning
9. Explainable AI
强化学习纲要
1. Overview
2. Markov Decision Process (MDP)
3. Model-free prediction & control
4. Value Function Approximation
5. Policy Optimization Ⅰ
6. Plicy Optimization Ⅱ: SOTA
7. Model-based Reinforcement Learning
8. Imitation Learning
深度强化学习
1. Introduction of RL
2. Proximal Policy Optimization
3. Q-Learning
4. Actor-Critic
5. Sparse Reward
6. Imitation Learning
笔记本
README.md
介绍
////
This work is licensed under a
CC-BY-NC-SA 4.0 International License
.
Deployed by
GitHub Pages
. Powered by
Jekyll
. Based on
jekyll-rtd-theme
.
GitHub
main
Repository
Issues
Download ZIP
网页源码被
MIT License
开源协议保护
