@mahakloui: #ti̇ktok #وایرال #فوریو #fyb #fy

makak🐰
makak🐰
Open In TikTok:
Region: IR
Tuesday 23 June 2026 15:54:19 GMT
11529
1238
27
103

Music

Download

Comments

ix.yu9n4.3
Y o u n a :
اینجا هنوز عاشق کترین بود
2026-06-24 12:59:15
1
mobina9924
🧸mobina🦋 :
اشکم درومد😭
2026-06-24 11:57:27
0
merhrsa.mansoury
. :
از کجا میشه ببینم؟
2026-06-24 14:41:29
0
reyhann15555
reyhann15555 :
اسم فیلم؟
2026-06-24 09:36:43
0
setayesh1159
:( :
اسمشششششششش
2026-06-24 09:57:08
0
yasi5926
Yasi❤️ :
دیمن منننننن🥰🥰🥰 قربونتتتتت بشم عشق زندگیم
2026-06-23 23:06:34
3
meli_x2011
Melika :
اسم این فیلم چیه
2026-06-24 08:45:08
0
hasti_13922
hasti_1392 :
حاجی من تازه فیلمو شروع کردم میشه بگید الینا با کی وارد رابطه میشه؟
2026-06-24 15:08:24
0
setareh1296
☽ :
فیلمشو برام بفرس
2026-06-24 09:54:46
0
freshtahossyni
بانو سادات :
🥺🥺🥺
2026-06-24 14:48:08
0
To see more videos from user @mahakloui, please go to the Tikwm homepage.

Other Videos

🚨 Panicking because your AI's loss is going UP? Don't. It might actually be getting smarter.
 
 If you are transitioning from standard Deep Learning to Reinforcement Learning, you have probably stared at your TensorBoard in absolute confusion. Your agent is surviving longer, your rewards are increasing, but your loss is oscillating wildly and growing in magnitude. 
 
 Here is the First Principle you need to understand: **In RL, Loss $\neq$ Error.**
 
 🧠 **The Quick-Win Mental Model:**
 Think of your RL training like driving a car.
 🏎️ **Loss = The Steering Wheel.** It fluctuates left and right (positive and negative) to adjust the probabilities of your AI's actions. A steering wheel at zero just means you aren't turning.
 ⏱️ **Average Reward = The Speedometer.** This is the ONLY metric that tells you if you are actually moving toward your goal.
 
 ⚠️ **Crucial Rule:** Never square your negative returns to make them positive like you would with MSE. Squaring a -50 penalty turns it into a +2500 reward. You will literally teach your AI to jump off a cliff! Swipe through the carousel to see exactly why. 👉
 
 📚 **The Math Behind the Magic:**
 Want to see the beautiful calculus that makes this work? I just published a complete Deep-Dive on Substack where we derive the Policy Gradient Theorem from scratch. We break down the famous
🚨 Panicking because your AI's loss is going UP? Don't. It might actually be getting smarter. If you are transitioning from standard Deep Learning to Reinforcement Learning, you have probably stared at your TensorBoard in absolute confusion. Your agent is surviving longer, your rewards are increasing, but your loss is oscillating wildly and growing in magnitude. Here is the First Principle you need to understand: **In RL, Loss $\neq$ Error.** 🧠 **The Quick-Win Mental Model:** Think of your RL training like driving a car. 🏎️ **Loss = The Steering Wheel.** It fluctuates left and right (positive and negative) to adjust the probabilities of your AI's actions. A steering wheel at zero just means you aren't turning. ⏱️ **Average Reward = The Speedometer.** This is the ONLY metric that tells you if you are actually moving toward your goal. ⚠️ **Crucial Rule:** Never square your negative returns to make them positive like you would with MSE. Squaring a -50 penalty turns it into a +2500 reward. You will literally teach your AI to jump off a cliff! Swipe through the carousel to see exactly why. 👉 📚 **The Math Behind the Magic:** Want to see the beautiful calculus that makes this work? I just published a complete Deep-Dive on Substack where we derive the Policy Gradient Theorem from scratch. We break down the famous "Log-Derivative Trick" and show how this exact math forms the foundation of PPO—the algorithm OpenAI uses to align ChatGPT. 🔗 **Link in bio to read the full mathematical proof!** 👇 **Question for you:** Have you ever accidentally trained an AI to do the exact opposite of what you wanted? Tell me your funniest RL fail in the comments! #reinforcementlearning #machinelearning #deeplearning #artificialintelligence #math

About