51616

split-vae

Original implementation of Separated Paths for Local and Global Information framework (SPLIT) in TensorFlow 2.

marl-lipo

Official codebase for Generating Diverse Cooperative Agents by Learning Incompatible Policies (notable-top-25% @ ICLR 2023)

openai_requests_for_research

My attemp to do requests for research from OpenAI

vim

Vim config and bundle

wordwar

Object oriented game using java

51616

51616.github.io

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

advent_of_code_2019

My solution for advent of code 2019 in python

aoc2020

my solution for Advent of Code 2020

attentionneuron.github.io

baselines

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

boids

boids!

brax

Massively parallel rigidbody physics simulation on accelerator hardware.

cleanba

CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL

cleanrl

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

dotfiles

dreamerv2

Mastering Atari with Discrete World Models

envpool

C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.

es-clip.github.io

Placeholder

evojax

fort

My utility repo for personal work (multi-agent reinforcement learning)

github-pages-javascript-prototype

Experimenting with GitHub pages and JavaScript and local data

gsa-scraper

This codebase implements a scraper that accumulate all GSA emails from your inbox into a single `.md` file.

human_aware_rl

Code for "On the Utility of Learning about Humans for Human-AI Coordination"

IsaacGymEnvs

Isaac Gym Reinforcement Learning Environments

multiagent_mujoco

Benchmark for Continuous Multi-Agent Robotic Control, based on OpenAI's Mujoco Gym environments.

PettingZoo

Gym for multi-agent reinforcement learning

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.

rebar

Reinforcement learning utils from https://github.com/andyljones/megastep

xmanager

A platform for managing machine learning experiments