Lygerakis Fotis

mvitac. Self-Supervised Visual-Tactile Representation Learning via Multimodal Contrastive Training

M2CURL. We propose Multimodal Contrastive Unsupervised RL (M2CURL), a method that learns efficient representations from visuotactile data, improving RL convergence speed and performance. M2CURL is versatile, compatible with various RL algorithms, and enhances learning efficiency in manipulation tasks in the Tactile Gym 2 simulator.

maze3d_collaborative. Human-Agent Collaborative Deep Reinforcement Learning

CSE6363_Machine_Learning. Machine Learning algorithms from-scratch implementation. It covers most Supervised and Unsupervised algorithms. Homework assignments and Projects for graduate level Machine Learning Course taught by Dr Manfred Huber at UTA during Spring 21

transf_chatbot_metalWOZ. Chatbot based on Multihead Attention on metal WOZ dataset using transfer learning

ur3_tactile_servoing. Real-time closed-loop tactile servoing for the UR3e robot using vision-based tactile sensors

tactile-perception-ros. ROS2 wrapper package for DIGIT and GelSight tactile sensors. Features include sensor discovery, image publishing (raw/compressed), OpenCV visualization, and tactile flow computation for force vector estimation from GelSight images.

maze_RL_v2. Python

H-AI_collab_game. Collaborative Reinforcement Learning on Human-Computer shared task

BipedalWalker_v2_ActorCritic_DQN. BipedalWalker-v2 enviroment from OpenAI gym using Actor-Critic Deep Q Netwok

CSE5306_Distributed_Systems_Project_3. TCP Server-Client communication for text annotation with redundancy, polling and back-up server for graduate level Distributed Systems Course taught by Chance Eary at UTA during Spring 21

BayesianStructureStructureLearning. Bayesian Network learning and validation

representation_learning_tutorial. Implementation of basic autoencoder architectures and SimCLRv2

maze_GI_Unity. Maze Game on Unity for Human-Computer Colalboration

crvae. This is the implementation of the paper: "CR-VAE: Contrastive Regularization on Variational Autoencoders for Preventing Posterior Collapse"

Implemantation_AES_PubKey_SHA_Signature. Implementation from scratch of the AES128, AES256, AES512, Public Key Cryptography, SHA256, SHA512,SHA384 and Signature and Verification mehods