Pinned Repositories
AI-Art-Generation
Generates art
AskMeAnything
EJGo
Predicting Go moves using a neural network
ludus
Minimalistic library to simplify and speed up application and Reinforcement Learning
multilingual-nmt-mt5
An example of multilingual machine translation using a pretrained version of mt5 from Hugging Face.
OSRS-Cow-Killing-AI
Q-Learning-Tutorials
RL-Representation
Algorithms and utilities I use for representation learning research
RL-template
Template for fast, efficient, and simple Reinforcement Learning
ejmejm's Repositories
ejmejm/multilingual-nmt-mt5
An example of multilingual machine translation using a pretrained version of mt5 from Hugging Face.
ejmejm/RL-template
Template for fast, efficient, and simple Reinforcement Learning
ejmejm/AI-Art-Generation
Generates art
ejmejm/ludus
Minimalistic library to simplify and speed up application and Reinforcement Learning
ejmejm/Q-Learning-Tutorials
ejmejm/OSRS-Cow-Killing-AI
ejmejm/Auto-Research
ejmejm/MuZero
A distributed and efficient implementation of MuZero using PyTorch and Ray.
ejmejm/RL-Representation
Algorithms and utilities I use for representation learning research
ejmejm/in-weight-memory
ejmejm/OsuMapGenerator
ejmejm/jp-flash-cards
ejmejm/adversarial-irl
Implementation of adversarial inverse reinforcement learning (AIRL).
ejmejm/crafter-ood-env
ejmejm/CrafterExperiments
Experimenting with the Crafter environment
ejmejm/dall-e-trainer
Training OpenAI's DALL-E
ejmejm/DeepSeek-Coder
DeepSeek Coder: Let the Code Write Itself
ejmejm/Drawing-Improver
ejmejm/dvae-language-gen
Using a discrete autoencoder to generate a language for describing images
ejmejm/EfficientZero
Branch of open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021.
ejmejm/gym-minigrid
Minimalistic gridworld package for OpenAI Gym
ejmejm/gym-puddle
Puddle world environment for OpenAI Gym.
ejmejm/knowledge-transfer-research
ejmejm/NeuralEmbeddings
Using self-supervised learning to create robust MEG and EEG embeddings
ejmejm/OptionsExplorationExperiments
Just is just some of my personal experimentation in the area of using options for exploration
ejmejm/Rainbow
Rainbow: Combining Improvements in Deep Reinforcement Learning
ejmejm/SkilledFeedbackExperiments
ejmejm/trl
Train transformer language models with reinforcement learning.
ejmejm/VirtualAssistantBase
ejmejm/youtube-scraper
Scrapes YouTube videos data to build a dataset.