RyanNavillus

Syllabus

Synchronized Curriculum Learning for RL Agents

reward-surfaces

PPO-v3

Adding Dreamer-v3's implementation tricks to CleanRL's PPO

AlphaSmash

Using AlphaRank to rank professional Super Smash Bros Melee competitors

SNNsim

A simulator of the Loihi architecture for testing Spiking Neural Network performance.

PufferLib

Simplifying reinforcement learning for complex game environments

ryannavillus.github.io

Thought-Cloning-CT

Fork of Thought Cloning: Learning to Think while Acting by Imitating Human Thinking

AutoROM

Install Atari ROMs for Gym/ALE-Py in 2 Commands

PettingZoo

Gym for multi-agent reinforcement learning

X-Ray-Segmentation-MSU-REU

National Science Foundation REU at Michigan State University Summer 2019

aws-ai-qna-bot

Code samples related to "Creating a Question and Answer Bot with Amazon Lex and Amazon Alexa", published on the AWS AI Blog. QnABot (pronounced “Q and A Bot”), uses Amazon Lex and Amazon Alexa to provide a conversational interface to your “Questions and Answers”, so users can just ask their questions and get quick and relevant answers.

classification_models

Classification models trained on ImageNet. Keras.

CMSC818G-Project

commonsense-rl

Knowledge-Aware RL agents with Commonsense Reasoning

dungeonsdata-neurips2022

Dataset Instructions and Tutorials for Submission to Neurips2022

gitignore

A collection of useful .gitignore templates

gym

A toolkit for developing and comparing reinforcement learning algorithms.

level-replay

This code implements Prioritized Level Replay, a method for sampling training levels for reinforcement learning agents that exploits the fact that not all levels are equally useful for agents to learn from during training.

Mid-SURE

Presentation Material for Mid-SURE Conference

nmmo-baselines

Baselines for Neural MMO -- new users should treat this repo as a starter project

openrlbenchmark

procgen

Procgen Benchmark: Procedurally Generated Game-Like Gym Environments

rl_scratch

sac

Soft Actor-Critic

segmentation_models

Segmentation models with pretrained backbones. Keras.

SPIE-QR

tcav

Code for the TCAV ML interpretability project

TilesAndTowers

Tiles. And Towers

Udacity

A collection of my Udacity Deep Learning Nanodegree Projects