egiob Goto Github PK

brax

Massively parallel rigidbody physics simulation on accelerator hardware.

cfrx

cfrx is a collection of algorithms and tools for hardware-accelerated Counterfactual Regret Minimization (CFR) algorithms in Jax.

csgo_forecasting

A project on predicting odds of CSGO (Counter Strike Global Offensive) games. I computed features and created a model which is meant to beat (at least some) bookmakers.

datacamp-assignment-pandas

Assignement for Datacamp on pandas.

datacamp-assignment1

datacamp-master

Datacamp class for master student - 1 week

diayn

diversityisallyouneed-sb3

Implementation of Diversity Is All You Need (DIAYN) on top of Stable Baselines 3.

gwg_release

Official release of code for "Oops I Took A Gradient: Scalable Sampling for Discrete Distributions"

gym

A toolkit for developing and comparing reinforcement learning algorithms.

gym-nav2d

A simple continuous 2d navigation task for few-shot RL tasks

jumanji

🕹️ A suite of diverse and challenging RL environments in JAX

mctx

Monte Carlo tree search in JAX

ml-agents

Unity Machine Learning Agents Toolkit

music

Mutual Information State Intrinsic Control (ICLR 2021 Spotlight)

open_spiel

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

par-ici-tennis

Book Paris tennis court

pgx

🎲 Vectorized RL game environments in JAX

ray

An open source framework that provides a simple, universal API for building distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library.

rl-baselines3-zoo

A collection of pre-trained RL agents using Stable Baselines3, training and hyperparameter optimization included.

sac

Soft Actor-Critic

skill_discovery

spotify_genre_challenge

A machine learning challenge which consists in predicting the genre of a music based on features from the Spotify API.

vq-vae-2-pytorch

Implementation of Generating Diverse High-Fidelity Images with VQ-VAE-2 in PyTorch