This note is just the Question and Answer of LUNG ADN RESPIRATION SYSTEM.
Introduction
This blog is my personal notebook as a first-year graduate student exploring:
- Fluid mechanics
- Computational fluid dynamics (CFD)
- Deep learning for scientific computing
- Reinforcement learning for control & optimization
The goals here are simple:
- Organize my own learning — notes, derivations, code, and experiment logs.
- Make things clearer — explanations my past self would understand.
- Track progress — from basics to more advanced topics over time.
This is not a polished tutorial site. Just a public working notebook — with mistakes, fixes and experiments.
Thanks for visiting, and welcome to this small corner of CFD & learning.
↓ Browse recent notesRL Note 8: Actor-Critic Method
Posted on
Edited on
In
Reinforcement Learning
Reinforcement Learning,
Actor-Critic Method,
Importance Sampling
Symbols count in article: 6.9k Reading time ≈ 6 mins.
Symbols count in article: 6.9k Reading time ≈ 6 mins.
This note wiil introduce Actor-Critic Method, which can basically seen as the combination of Value-based method and Policy-based method.
RL Note 7: Policy Gradient Method
Posted on
Edited on
In
Reinforcement Learning
Policy Gradient Method,
Reinforcement Learning，Sarsa,
REINFORCE
Symbols count in article: 4.3k Reading time ≈ 4 mins.
Symbols count in article: 4.3k Reading time ≈ 4 mins.
This note will illustrate the transition from value-based methods to policy-based methods. REINFORCE algorithm is introduced as well.
RL Note 6: Value Function Approximation
Posted on
Edited on
In
Reinforcement Learning
Reinforcement Learning,
SARSA,
Q-Learning,
Value Function Approximation,
Deep Q-Learning
Symbols count in article: 6.4k Reading time ≈ 6 mins.
Symbols count in article: 6.4k Reading time ≈ 6 mins.
This note wiil introduce the transition from table-based methods to function-based method.
RL Note 5: Temporal Difference Algorithm
Posted on
Edited on
In
Reinforcement Learning
Temporal Difference Algorithm,
SARSA,
Q-Learning
Symbols count in article: 8k Reading time ≈ 7 mins.
Symbols count in article: 8k Reading time ≈ 7 mins.
This note will introduce TD Algorithm and it's application in SARSA and Q-Learning.
RL Note 4: Stochastic Approximation
Posted on
Edited on
In
Reinforcement Learning
Reinforcement Learning,
Stochastic Approximation,
Robbins-Monro Algorithm,
Stochastic Gradient Descent
Symbols count in article: 6.6k Reading time ≈ 6 mins.
Symbols count in article: 6.6k Reading time ≈ 6 mins.
This note will mainly cover stochastic apprximation approaches, while introducing RM Algorithm and SGD Algorithm.
RL Note 3: Monte Carlo Estimation
Posted on
Edited on
In
Reinforcement Learning
Monte Carlo,
Reinforcement Learning
Symbols count in article: 7.9k Reading time ≈ 7 mins.
Symbols count in article: 7.9k Reading time ≈ 7 mins.
This note will mainly talk about the principle of MC Learning.
RL Note 2: Value Iteration & Policy Iteration
Posted on
Edited on
In
Reinforcement Learning
Value Iteration,
Policy Iteration
Symbols count in article: 6.1k Reading time ≈ 6 mins.
Symbols count in article: 6.1k Reading time ≈ 6 mins.
This note will explain vlaue interation & policy iteration
RL Note 1: Basic Concepts & Tools for RL
Posted on
Edited on
In
Reinforcement Learning
Reinforcement Learning,
Bellman Equation
Symbols count in article: 14k Reading time ≈ 12 mins.
Symbols count in article: 14k Reading time ≈ 12 mins.
This note will explain baisc concepts of RL and Bellman Equation.