piojanu
I'm eager for knowledge and driven forward by science 🤓 Working on Deep RL 🤖 Aiming to distil human intelligence into a lasting form ðŸ§
@allegro.euPoland
Pinned Repositories
AlphaZero
AlphaZero for Othello, Connect4, GoBang and TicTacToe using Keras and my HumbleRL framework.
CUDA-im2col-conv
CUDA project for uni subject
GradientAILab
Experiments with Deep Reinforcement Learning
humblerl
Straightforward reinforcement learning python framework
tf_utils
TensorFlow utilities
World-Models
Implementation of World Models: https://worldmodels.github.io.
piojanu's Repositories
piojanu/CUDA-im2col-conv
CUDA project for uni subject
piojanu/humblerl
Straightforward reinforcement learning python framework
piojanu/World-Models
Implementation of World Models: https://worldmodels.github.io.
piojanu/AlphaZero
AlphaZero for Othello, Connect4, GoBang and TicTacToe using Keras and my HumbleRL framework.
piojanu/tf_utils
TensorFlow utilities
piojanu/active-representation-learning
piojanu/AIGames_2020_Weather
AIGames 2020 - Weather Challenge
piojanu/BioInf-PG
Project from bioinformatics on PG
piojanu/Class_in_Bedlewo_2020
EDA, Data Cleaning, ML, DL
piojanu/dotfiles
dotfiles for my systems
piojanu/dvc.org
🔗 DVC website and documentation
piojanu/edward2
A simple probabilistic programming language.
piojanu/EmacsIDE-v2
Second version of Emacs IDE, created after move to Mac.
piojanu/football
Check out the new game server:
piojanu/hugo-coder
A minimalist blog theme for hugo.
piojanu/ilqr
Iterative Linear Quadratic Regulator with auto-differentiatiable dynamics models
piojanu/Introduction-to-RL
piojanu/mrunner
piojanu/mujoco-py
MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.
piojanu/neptune-contrib
Tools, helpers and everything else that helps you work with Neptune.
piojanu/Parallel-Bandits
piojanu/planet
Deep Planning Network: Control from pixels by latent planning with learned dynamics
piojanu/Planning-in-Deep-Reinforcement-Learning
Presented at: Imperial College London for Students for AI, PyCode Conference 2018 and International Summer School on Deep Learning 2018
piojanu/Planning-in-Imagination
piojanu/ray
A fast and simple framework for building and running distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library.
piojanu/resume-website
piojanu/RLlogging
piojanu/Streamlined-Off-Policy-Learning
ICRL 2020
piojanu/tree-of-reference
My papers reading tree of reference
piojanu/Zotero2Readwise-Sync
An automated and scheduled trigger of Zotero2Readwise Python library (https://github.com/e-alizadeh/Zotero2Readwise)