ejmejm

multilingual-nmt-mt5

An example of multilingual machine translation using a pretrained version of mt5 from Hugging Face.

RL-template

Template for fast, efficient, and simple Reinforcement Learning

AI-Art-Generation

Generates art

ludus

Minimalistic library to simplify and speed up application and Reinforcement Learning

Q-Learning-Tutorials

Auto-Research

in-weight-memory

MuZero

A distributed and efficient implementation of MuZero using PyTorch and Ray.

RL-Representation

Algorithms and utilities I use for representation learning research

OsuMapGenerator

CLAgent

Continual learning agent

jp-flash-cards

adversarial-irl

Implementation of adversarial inverse reinforcement learning (AIRL).

crafter-ood-env

CrafterExperiments

Experimenting with the Crafter environment

dall-e-trainer

Training OpenAI's DALL-E

DeepSeek-Coder

DeepSeek Coder: Let the Code Write Itself

discrete-representations-for-continual-rl

Code for the paper "Harnessing Discrete Representations for Continual Reinforcement Learning"

dvae-language-gen

Using a discrete autoencoder to generate a language for describing images

EfficientZero

Branch of open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021.

gym-minigrid

Minimalistic gridworld package for OpenAI Gym

gym-puddle

Puddle world environment for OpenAI Gym.

knowledge-transfer-research

NeuralEmbeddings

Using self-supervised learning to create robust MEG and EEG embeddings

OptionsExplorationExperiments

Just is just some of my personal experimentation in the area of using options for exploration

Rainbow

Rainbow: Combining Improvements in Deep Reinforcement Learning

SkilledFeedbackExperiments

trl

Train transformer language models with reinforcement learning.

VirtualAssistantBase

youtube-scraper

Scrapes YouTube videos data to build a dataset.