✕ Clear all filters
20 articles
▶ Videos →

📰 Medium · Deep Learning

20 articles · Updated every 3 hours · View all reads

All Articles 167,848Blog Posts 160,036Tech Tutorials 44,533Research Papers 32,781News 21,441 ⚡ AI Lessons
From REINFORCE to PPO: Every Policy Gradient Trick Is a Variance Story
Medium · Deep Learning 🎮 Reinforcement Learning ⚡ AI Lesson 2w ago
From REINFORCE to PPO: Every Policy Gradient Trick Is a Variance Story
No code, no derivations. Just the one idea that connects every algorithm in the family. Continue reading on Medium »
View lesson → + Playlist
What Is Reinforcement Learning? A Beginner’s Guide to AI That Learns by Trial and Error
Medium · Deep Learning 🎮 Reinforcement Learning ⚡ AI Lesson 2w ago
What Is Reinforcement Learning? A Beginner’s Guide to AI That Learns by Trial and Error
How do AI systems learn to make decisions on their own? Reinforcement Learning is a powerful branch of Artificial Intelligence where… Continue reading on Medium
View lesson → + Playlist
On-Policy vs Off-Policy Learning: The Most Misunderstood Distinction in Reinforcement Learning
Medium · Deep Learning 🎮 Reinforcement Learning ⚡ AI Lesson 3w ago
On-Policy vs Off-Policy Learning: The Most Misunderstood Distinction in Reinforcement Learning
From TD errors to GRPO — explained in words, with all the algebra kept in one place at the end, Continue reading on Medium »
View lesson → + Playlist
Nobody Invented PPO From Scratch
Medium · Deep Learning 🎮 Reinforcement Learning ⚡ AI Lesson 3w ago
Nobody Invented PPO From Scratch
Reinforcement learning algorithms are usually taught as a list. But each one exists because the previous one had a specific, painful… Continue reading on Medium
View lesson → + Playlist
Making RL agent complex is not the same as making it smart!
Medium · Deep Learning 🎮 Reinforcement Learning ⚡ AI Lesson 4w ago
Making RL agent complex is not the same as making it smart!
Using Contextual bandits to solve the Tragedy of commons. Continue reading on Medium »
View lesson → + Playlist
Medium · Deep Learning 🎮 Reinforcement Learning ⚡ AI Lesson 1mo ago
What exactly is Reinforcement Learning ?
Recently I came across the yt video, “AI Olympics- multi agent Reinforcement Learning” by AI Warehouse channel. Continue reading on Medium »
View lesson → + Playlist
Modern Reinforcement Learning
Medium · Deep Learning 🎮 Reinforcement Learning ⚡ AI Lesson 1mo ago
Modern Reinforcement Learning
Part I: Core Foundations Continue reading on Medium »
View lesson → + Playlist
Why Reinforcement Learning Is Harder in Trading Than in Games Like Chess
Medium · Deep Learning 🎮 Reinforcement Learning ⚡ AI Lesson 2mo ago
Why Reinforcement Learning Is Harder in Trading Than in Games Like Chess
The Fundamental Difference Between Beating a Grandmaster and Beating the Market Continue reading on InsiderFinance Wire »
View lesson → + Playlist
Medium · Deep Learning 🎮 Reinforcement Learning 2mo ago
Understanding Value Functions, Bellman Equation, and Learning in Reinforcement Learning
Introduction Continue reading on GoPenAI »
Read article → + Playlist
Learning by messing up: A beginner’s tour of Reinforcement Learning
Medium · Deep Learning 🎮 Reinforcement Learning ⚡ AI Lesson 2mo ago
Learning by messing up: A beginner’s tour of Reinforcement Learning
From agents and rewards all the way to the Markov property and your first Gym environment, written like the notes you wish someone had… Continue reading on Medi
View lesson → + Playlist
A very simple explanation of The Gambler’s Problem in Reinforcement Learning
Medium · Deep Learning 🎮 Reinforcement Learning ⚡ AI Lesson 2mo ago
A very simple explanation of The Gambler’s Problem in Reinforcement Learning
This article is based on Example 4.3 from Sutton and Barto’s Reinforcement Learning: An Introduction, one of the most widely read… Continue reading on Medium »
View lesson → + Playlist
Reinforcement Learning Explained Simply: How Machines Learn Through Rewards
Medium · Deep Learning 🎮 Reinforcement Learning ⚡ AI Lesson 3mo ago
Reinforcement Learning Explained Simply: How Machines Learn Through Rewards
Artificial Intelligence is evolving rapidly, and one of the most fascinating areas in AI is Reinforcement Learning (RL). Continue reading on Medium »
View lesson → + Playlist
Medium · Deep Learning 🎮 Reinforcement Learning ⚡ AI Lesson 3mo ago
Reinforcement Learning
PPO (Proximal Policy Optimization) Continue reading on Medium »
View lesson → + Playlist
Medium · Deep Learning 🎮 Reinforcement Learning ⚡ AI Lesson 3mo ago
Building Adaptive Game AI with Reinforcement Learning in Unity
Most enemies in video games are predictable. Continue reading on Medium »
View lesson → + Playlist
Reinforcement Learning: Teaching Machines Through Rewards and Experience
Medium · Deep Learning 🎮 Reinforcement Learning 3mo ago
Reinforcement Learning: Teaching Machines Through Rewards and Experience
Introduction Continue reading on Medium »
Read article → + Playlist
PPO Isn’t Boring. It’s What Happens When Reinforcement Learning Grows Up.
Medium · Deep Learning 🎮 Reinforcement Learning ⚡ AI Lesson 4mo ago
PPO Isn’t Boring. It’s What Happens When Reinforcement Learning Grows Up.
The algorithm that keeps winning by refusing to do anything too stupid, too fast Continue reading on Medium »
View lesson → + Playlist
Choosing the Right Reinforcement Learning Algorithm (Without Guessing)
Medium · Deep Learning 🎮 Reinforcement Learning ⚡ AI Lesson 4mo ago
Choosing the Right Reinforcement Learning Algorithm (Without Guessing)
Reinforcement Learning (RL) looks glamorous until you actually try to apply it. Then reality hits: which algorithm should you even use… Continue reading on Medi
View lesson → + Playlist
The Four Conditions: A Framework for Making Correctness the Path of Least Resistance in RLVR
Medium · Deep Learning 🎮 Reinforcement Learning ⚡ AI Lesson 4mo ago
The Four Conditions: A Framework for Making Correctness the Path of Least Resistance in RLVR
You can read every RLVR paper from the last two years — DeepSeek-R1, DAPO, SCOPE, the Tsinghua mode-collapse analysis, the reward hacking… Continue reading on M
View lesson → + Playlist
Harmless Exploration Is a Dangerous Myth
Medium · Deep Learning 🎮 Reinforcement Learning ⚡ AI Lesson 4mo ago
Harmless Exploration Is a Dangerous Myth
Why “just let the agent explore” breaks down fast when reinforcement learning touches robots, medicine, vehicles, and other high-stakes… Continue reading on Med
View lesson → + Playlist
The Death of RLHF: A Practitioner’s Guide to the New Post-Training Stack
Medium · Deep Learning 🎮 Reinforcement Learning ⚡ AI Lesson 4mo ago
The Death of RLHF: A Practitioner’s Guide to the New Post-Training Stack
GRPO, DAPO, and RLVR didn’t just improve on RLHF — they replaced it. Here’s why the old recipe broke, and what’s actually shipping now. Continue reading on Towa
View lesson → + Playlist