Interactive RL course in four parts: model the world as an MDP, solve it, learn without a model, scale up to deep RL.
Etienne Chassaing
cetiennec
AI & ML interests
Robotics, locomotion and imitation learning
Recent Activity
updated a Space about 18 hours ago
cetiennec/lerobot-for-companies updated a Space about 18 hours ago
cetiennec/rl-markov-decision-processes updated a dataset 1 day ago
cetiennec/microduck-article-demoOrganizations
Robotics lessons
Robotics basics and LeRobot: lessons and presentations.
Mathematics Foundations β Albert School
Course hub, slides and the interactive spaces of the maths-for-ML course.
- Running5
Teaching
π5Slides, exercise sheets and interactive spaces of my courses
- Running
How a Neural Network Learns
πThe chain rule, the gradient and gradient descent, by hand
- Running
PCA Explorer
π§Principal Component Analysis in 2D and 3D, live
- Running
The Forward Pass
γ°Turn the knobs of a network and see what shapes it can draw
LeRobot & Hugging Face for companies
What LeRobot and the Hugging Face Hub can do for your company: from a first low-cost arm to fine-tuned robot policies.
- Running on CPU Upgrade2
LeRobot for Companies
π€2How LeRobot and Hugging Face help companies start robotics
- Running
Robot Setup Advisor
π¦ΎRight-size a robot, GPU and board; compare cost, energy, CO2
- Running1
LeRobot Presentation
π€1Explore robot learning workflow through an interactive web demo
Reinforcement Learning β CentraleSupΓ©lec
Course hub, slides and the interactive spaces of the RL course (MDPs to deep RL).
- Running5
Teaching
π5Slides, exercise sheets and interactive spaces of my courses
- Running
Gridworld β Dynamic Programming
π§Policy evaluation, policy and value iteration, step by step
- Running
Jack's Car Rental β Policy Iteration
πPolicy iteration on Jack's Car Rental, step by step
- Running
Model-Free Control β MC, SARSA, Q-learning
π¬MC control, SARSA and Q-learning, step by step
Reinforcement Learning, from MDPs to Deep RL
Interactive RL course in four parts: model the world as an MDP, solve it, learn without a model, scale up to deep RL.
LeRobot & Hugging Face for companies
What LeRobot and the Hugging Face Hub can do for your company: from a first low-cost arm to fine-tuned robot policies.
- Running on CPU Upgrade2
LeRobot for Companies
π€2How LeRobot and Hugging Face help companies start robotics
- Running
Robot Setup Advisor
π¦ΎRight-size a robot, GPU and board; compare cost, energy, CO2
- Running1
LeRobot Presentation
π€1Explore robot learning workflow through an interactive web demo
Robotics lessons
Robotics basics and LeRobot: lessons and presentations.
Reinforcement Learning β CentraleSupΓ©lec
Course hub, slides and the interactive spaces of the RL course (MDPs to deep RL).
- Running5
Teaching
π5Slides, exercise sheets and interactive spaces of my courses
- Running
Gridworld β Dynamic Programming
π§Policy evaluation, policy and value iteration, step by step
- Running
Jack's Car Rental β Policy Iteration
πPolicy iteration on Jack's Car Rental, step by step
- Running
Model-Free Control β MC, SARSA, Q-learning
π¬MC control, SARSA and Q-learning, step by step
Mathematics Foundations β Albert School
Course hub, slides and the interactive spaces of the maths-for-ML course.
- Running5
Teaching
π5Slides, exercise sheets and interactive spaces of my courses
- Running
How a Neural Network Learns
πThe chain rule, the gradient and gradient descent, by hand
- Running
PCA Explorer
π§Principal Component Analysis in 2D and 3D, live
- Running
The Forward Pass
γ°Turn the knobs of a network and see what shapes it can draw