FelipeMartins96

ddpg-jax

rsoccer-isaac-cleanrl

armv8-assembly

Code exercises in ARMv8 Assembly language

IsaacGymEnvs

Isaac Gym Reinforcement Learning Environments

rl-agents-pytorch

rl-jax

Reinforcement learning algorithms implemented using the JAX library.

agents

My own development of Reinforcement Learning methods using Pytorch

brax

Massively parallel rigidbody physics simulation on accelerator hardware.

bsuite

bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent

IN1102_AM_fatc_2019.2

courses_assignments

dopamine

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

dylam_ddpg

exploring-deep-marl-in-ieee-vsss-recordings

FIRASim

~ FIRACup Soccer Simulator

in1100-agentes-cognitivos

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

larc-unification-scripts

PettingZoo

Gym for multi-agent reinforcement learning

play_fira

rl-pytorch

rSoccer

🎳 Environments for Reinforcement Learning

rsoccer-isaac

slurm-tests-docker

ssl-simulation-setup

Documentation and sources for a virtual tournament setup

ssl-vision

Shared Vision System For The RoboCup Small Size League

VSSReferee

The VSS-Referee is the automatic referee module created to IEEE Very Small Size Soccer League, creating the possibility to teams catch the data coming from it and replace strategically their robots, decreasing the human necessity at the field.

VSSSLogPlayer

The VSSSLogPlayer is an log tool created to IEEE Very Small Size Soccer League, aiming the possibility to play recorded logs and reproduce them in the network.