RL-Lab @_RL_Lab_

Learn and practice Reinforcement Learning in a funny and playful way. Visit https://t.co/qAmM4k3gcX Joined December 2021

Tweets

47
Followers

38
Following

191
Likes

14

Ziad Salloum @zsalloum

4 years ago

#reinforcementlearning #education #learning #Motivation #selfimprovement towardsdatascience.com/tips-on-how-to…

1 1 1 0 0

#DQN by Mnih [2015] is a jumpstart and building block for many deep reinforcement learning algorithms. However, despite its simplicity on the surface, nevertheless, it represents challenges when implementing it. #reinforcementlearning #algorithms zsalloum.medium.com/practical-guid…

1 1 1 0 0

RL-Lab @_RL_Lab_

4 years ago

Also coming soon in the #cartpole labunit. DIY, an easy way for beginners to code #DQN #algorithm using Tensorflow.js #ReinforcementLearning is fun, give it a try. youtube.com/watch?v=qdg10a…

0 0 1 0 0

Oliver Cameron @olivercameron

4 years ago

Here's @ylecun in 1993(!) demoing LeNet-1. This was the world's first convolutional neural network for handwriting recognition. Today—29 years later—this same approach powers the majority of computer vision. Such a historical moment, and breakthrough for machine learning.

16 772 3K 0 243

Download Video

RL-Lab @_RL_Lab_

4 years ago

#CartPole is available. Uses #DeepReinforcementLearning & #DQN. Check it rl-lab.com/cartpole Train #AI to win #coursera #edXOnline #udemy #pluralsight #udacity #OpenClassrooms #openlrning #MasterClass #FutureLearn #Alison_Learning #GA #skillshare #VectorPerform #Codecademy

0 1 0 0 0

Download Image

RL-Lab @_RL_Lab_

4 years ago

Your job in the next unitlab #cartpole, is to configure or write an #AI that keeps the rod balanced on the cart until the total rewards reaches 300. Don't make it fall more than 30° from the vertical, and don't let the cart reaches the edges. Stay tuned #reinforcementlearning

0 1 2 0 0

Download Video

RL-Lab @_RL_Lab_

4 years ago

labunit #cartpole is taking shape. It is the next labunit on RL-lab.com it uses #DQN algorithm #reinforcementlearning is great. #AI #deeplearning #machinelearning

0 0 0 0 0

Download Image

RL-Lab @_RL_Lab_

4 years ago

_rl_lab_ Next lab unit is about keeping balance. Coming soon RL-Lab.com #reinforcementlearning #deepreinforcementlearning #deeplearning #machinelearning #Airdrop #COMING_SOON

0 0 0 0 0

Download Image

RL-Lab @_RL_Lab_

4 years ago

very good explanation of #DQN. Grokking #ReinforcementLearning by Miguel Morales @mimoralea amazon.com/Grokking-Reinf… #deeplearning #machinelearning

0 0 1 0 0

Download Image

RL-Lab @_RL_Lab_

4 years ago

#Exploration / #Exploitation average/distinct rewards #reinforcementlearning. rl-lab.com/multi-armed-ba… @coursera @edXOnline @udemy @pluralsight @udacity @OpenClassrooms @openlrning @MasterClass @FutureLearn @Alison_Learning @GA @skillshare @VectorPerform @Codecademy

0 1 1 0 0

Download Image

RL-Lab @_RL_Lab_

4 years ago

#stationary / #nonstationary #exploration vs #exploitation dilemma #reinforcementlearning rl-lab.com/multi-armed-ba… @coursera @edXOnline @udemy @pluralsight @udacity @OpenClassrooms @openlrning @MasterClass @FutureLearn @Alison_Learning @skillshare @VectorPerform @Codecademy @GA

0 0 0 0 0

Download Image

RL-Lab @_RL_Lab_

4 years ago

#Exploration / #Exploitation with multi-armed bandits #reinforcementlearning. rl-lab.com/multi-armed-ba… @coursera @edXOnline @udemy @pluralsight @udacity @OpenClassrooms @openlrning @MasterClass @FutureLearn @Alison_Learning @GA @skillshare @VectorPerform @Codecademy @FutureLearn

0 1 1 0 0

Download Image

RL-Lab @_RL_Lab_

4 years ago

Experiment #exploration/#exploitation dilemma at rl-lab.com/multi-armed-ba… @coursera @edXOnline @udemy @pluralsight @udacity @OpenClassrooms @openlrning @MasterClass @FutureLearn @Alison_Learning @LinkedIn @GA @skillshare @VectorPerform @Codecademy @FutureLearn

0 1 1 0 0

Download Image

RL-Lab @_RL_Lab_

4 years ago

The next #experiment #multiarmed #bandits or #slotmachine is slowly taking shape. It is a #cornerstone experiment in #reinforcementlearning, because it will help figure out how much to #explore and how much to #exploit. Stay tuned

0 1 3 0 0

Download Image

RL-Lab @_RL_Lab_

4 years ago

SOON: Multi-armed Bandits. Important feature in #ReinforcementLearning different than other learnings is the need for active #exploration & #evaluative #feedback. k-armed bandit problem introduce a number of basic learning methods #ai #artificialintelligence #mutli #arm #bandit

0 4 0 0 0

Download Image

RL-Lab @_RL_Lab_

4 years ago

#ReinforcementLearning #students you can practice your skills on rl-lab.com @coursera @edXOnline @udemy @pluralsight @udacity @OpenClassrooms @openlrning @MasterClass @FutureLearn @Alison_Learning @LinkedIn @GA @skillshare @VectorPerform @Codecademy @FutureLearn

0 1 1 0 0

Ziad Salloum @zsalloum

4 years ago

Tinkering with #MonteCarlo Method in #ReinforcementLearning Pushing the limits with special cases and practical examples from rl-lab.com/gridworld-mc @TDataScience @_RL_Lab_ #MachineLearning #ArtificialIntelligence #TDS towardsdatascience.com/tinkering-with…

0 3 1 0 0

Google DeepMind @GoogleDeepMind

4 years ago

We are honoured that #AlphaFold has been named Breakthrough of the Year and People's Choice by @ScienceMagazine. Huge congratulations to the team, our partners, and to those around the world building on this work to accelerate biological research. On to 2022!