ErnestBeckham's repositories
AI-Laplace-2D
This repo contains study of reinforcement learning algorithms for 2D car racing
transformer
This repo contains implementation of transformer
snake-AI
This repo contains implementation of RL algorithms to play snake game.
Deep-Inverse-Reinforcement-Learning
This repo contains implementation and study of Deep inverse RL.
KAN-Agents
This repo contains deep reinforcement learning agents with kolmogorov-arnold network (KAN).
mini-Llama
This repo contains implementation of Mini version of Llama by using Umar Jamil video about Llama 2 implementation
large-language-model-creation
This repo contains full creation of LLM (pre-training, supervised fine tuning, RLHF)
Mixture-of-LLM-Expert
This repo contains implmentation and study of mixture of expert in LLM.
Actor-Critic-RNN
This repo contains implementation of actor critic intergrated with RNN for continous and discrete action spaces
2D-ASR
This repo contains research and experiment of 2D artificial sensors using pygame. ASR represents Artificial Sensor Research. This study can helps to integrate arificial sensors within 2D environment for RL and multi-agent.
Does-vision-pre-training-contribute-to-XAI
This repo contains study of how vision pre-training helps to eXplainable AI
Mixture-of-Medical-Expert
This repo contains adapt Mixture of Experts to Medical Images classification
behaviour-cloning
This project is study of various algorithm for behaviour cloning
Unet-in-AutoEncoder
This repo contains study of integration unet in autoencoder and generate images
CustomEnv
This repo contain environment for reinforcement learning training.
end-to-end-game-engagement-classification-project
This project is classification of game engagement using deep learning. in this project docker, FastAPI and several security technique used for study purpose.
unsupervised-pre-training-vgg
This repo contain study of pre-training vgg using autoencoder for brain tumor and XAI
Mixture-of-Expert
This is repo contain study and implementation of Mixture of Experts using pytorch and tensorflow
siameseTransformer
This repository contains a study on the combination of Siamese networks and Transformers
L2RPN-case5-study
This repo contains study of KAN intergrated RL agents for l2rpn(learning to run power network) challenege.
project-koperundevi
This project is a study of LLMs (Large Language Models) for the Tamil language.
siamese-network
This Repo contain siamese network variants
Iseg
This is the library for image segmentation task. This library has many architecture for image segmentation.
Transformers
This repo contains transformers architectures
L2RPN-case14
This project is creating agent for L2RPN case 14.
Zeros
This project is implementing AlphaZero and MuZero for research purpose.
L2RPN-rte-5
This repository contains implementations of various reinforcement learning algorithms, including DQN, graph-based RL, Actor-Critic, and PPO, specifically designed for the L2RPN challenge.
l2rpn-offline-reinforcement-learning
This repository contains implementations of various Offline reinforcement learning algorithms, including CQL and offline DQN, specifically designed for the L2RPN challenge.