raphaelavalos Goto Github PK

aml-lab

This repository contains the labs of AML course at Eurecom (Spring 2018). Those labs are done with Hugo Yeche. (Mirror repository of bitbucket)

arch-pkg

arch-repo

attention_tsp_graph_net

Implementation of Attention Solves Your TSP, Approximately (W. Kool et al.) with the DeepMind's Graph Nets library

cgt-assignment-3

cgt-assignment-3-2

VUB CGT assignement 3 - 2nd session

cgt2022-assignment-3

VUB CGT 2022 assignement 3

coma_rllib

Implentation of COMA using RLlib.

deeprl-doom

Implementation of Learning to Act by Predicting the Future (Alexey Dosovitskiy, Vladlen Koltun)

exceptionalrl

flow

Computational framework for reinforcement learning in traffic control

gotify-server

A simple server for sending and receiving messages in real-time per WebSocket. (Includes a sleek web-ui)

gym-rubikscube

Gym Environment for the Rubik's Cube

jumanji

🕹️ A diverse suite of scalable reinforcement learning environments in JAX

learning-dqn

maac_rllib

RLlib implementation of Iqbal and Sha "Actor-Attention-Critic for Multi-Agent Reinforcement Learning" 2019.

mlflow

Open source platform for the machine learning lifecycle

multiagent-particle-envs

Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"

mva-deep-learning

Homework for DeepLearning class of Vincent Lepetit

object-recognition

Object Recognition for the MVA course

pettingzoo

Gym for multi-agent reinforcement learning

popgym

probabilistic-graphical-models

Probabilistic Graphical Models

radicale

A simple CalDAV (calendar) and CardDAV (contact) server.

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.

reinforcementlearning

rl

RL experiments

rlpyt

Reinforcement Learning in PyTorch

rode

Codes accompanying the paper "RODE: Learning Roles to Decompose Multi-Agent Tasks (ICLR 2021, https://arxiv.org/abs/2010.01523). RODE is a scalable role-based multi-agent learning method which effectively discovers roles based on joint action space decomposition according to action effects, establishing a new state of the art on the StarCraft multi-agent benchmark.

vaia_rl

VAIA RL course and tutorial.