ascane/reinforcement-learning

Stars
1
Language
MATLAB
Created almost 8 years ago
Updated almost 8 years ago

ascane/reinforcement-learning

ascane

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

The repository contains my solutions including code and report to practical sessions (aka TP in French) of Reinforcement Learning.

gym-gazebo-hsr

An OpenAI gym environment based on Gazebo and ROS for Human Support Robot (HSR)

variational-methods-for-inference

In this project, we study variational methods for inference. We consider the Ising model on a grid. We then compare it with the following methods: Gibbs sampling, blocked Gibbs sampling, Loopy belief propagation, mean field.

sacq-hsr

SAC-Q on Human Support Robot

reaching-through-latent-space

Non-official codebase for Reaching Through Latent Space.

sparse-pca

In this project, we study the statistical and computational trade-offs in estimation of sparse principal components. In particular, we compute the semidefinite relaxation estimator and repeat the numerical experiments done in the following paper by T. Wang et al. https://arxiv.org/abs/1408.5369

lets-go

In this project, we study the immediate versus delayed reward for the game Go.

ascane.github.io

probabilistic-graphical-models

The repository contains my solutions to homework assignments of Probabilistic Graphical Models.

Jupyter Notebook

snake

Play the classic snake game in the terminal - ubuntu.

time-series-forecasting

Signal processing End-of-module open assignment -- Times series forecasting.

bunny-dimension-library

A library that provides templates, common data structures and algorithms aiming to compete in programming competitions.