Jogima-cyber
Master Student in Computer Science at Ecole Normale Supérieure (Ulm, ENS-PSL). Special focus on deep learning and particularly on deep reinforcement learning.
Paris, France
Pinned Repositories
2048
A small clone of 1024 (https://play.google.com/store/apps/details?id=com.veewo.a1024)
2048-TDLearning
Personal implementation in C++ of http://www.cs.put.poznan.pl/mszubert/pub/szubert2014cig.pdf. Results could be reproduced. It's an algorithm that learns by itself to solve the 2048 game. It doesn't use deep learning (aka. neural networks). But it learns by itself using the Bellman equations.
cleanrl
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
commentjava
The most french java parser
ContentAddr.Azure
Azure storage support for Lokad.ContentAddr
HandyRL
HandyRL is a handy and simple framework based on Python and PyTorch for distributed reinforcement learning that is applicable to your own environments.
inria-beamer
My L3 presentation of my summer research internship at INRIA on reinforcement learning
portfolio-manager
Python DQN for practicable portfolio management
sysres
Jogima-cyber's Repositories
Jogima-cyber/portfolio-manager
Python DQN for practicable portfolio management
Jogima-cyber/2048
A small clone of 1024 (https://play.google.com/store/apps/details?id=com.veewo.a1024)
Jogima-cyber/2048-TDLearning
Personal implementation in C++ of http://www.cs.put.poznan.pl/mszubert/pub/szubert2014cig.pdf. Results could be reproduced. It's an algorithm that learns by itself to solve the 2048 game. It doesn't use deep learning (aka. neural networks). But it learns by itself using the Bellman equations.
Jogima-cyber/cleanrl
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
Jogima-cyber/commentjava
The most french java parser
Jogima-cyber/ContentAddr.Azure
Azure storage support for Lokad.ContentAddr
Jogima-cyber/HandyRL
HandyRL is a handy and simple framework based on Python and PyTorch for distributed reinforcement learning that is applicable to your own environments.
Jogima-cyber/inria-beamer
My L3 presentation of my summer research internship at INRIA on reinforcement learning
Jogima-cyber/sysres