goncamateus

graduationMgm

Graduation Degree is comming

patocin

Duckietown agent developed by Researches at Centro de Informatica UFPE

agents

My own development of Reinforcement Learning methods using Pytorch

ddpg_sim2d

iai

Estudos sobre agentes inteligentes

Planning-the-path-with-rl

Study of Reinforcement Learning in the tasks of Path and trajectory planning in the RoboCup Small Size League environment

time_series

Projeto da cadeira de séries temporais 2020.2

sim2d_game_analyzer

Games analyzer for Robocup Simulation 2d.

cmoveis

projeto de cmoveis

compilers-cin

Teaching material for introduction to compilers course at UFPE

DLN

low-light image enhancement

gym

A toolkit for developing and comparing reinforcement learning algorithms.

gym-docs

Code for Gym documentation website

gym-line-follower

Line follower robot simulator environment for Open AI Gym.

jax-studies

Personal studies around jaxlib and sublibs

librcsc

ML

multiagent-particle-envs

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

mylibrcsc

pytorch-soft-actor-critic

PyTorch implementation of soft actor critic

rcssserver

RoboCup 2D Soccer Server

research

Own research on RL. Using to check some cool stuff for RoboCup Soccer Simulation 2D

rl-agents-pytorch

rl_studies

colaborative summary of reinforcement learning papers

ros2-Studies

rSoccer

🎳 Environments for Reinforcement Learning

sac

Implementation of Soft Actor Critic

scikit-learn

scikit-learn: machine learning in Python

sequential_social_dilemma_gym

Reproduction of https://github.com/eugenevinitsky/sequential_social_dilemma_games in fully OpenAI GYM

Site_Apuana

Documentação Cluster Apuana