Lygerakis Fotios's repositories
maze3d_collaborative
Human-Agent Collaborative Deep Reinforcement Learning
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.
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
H-AI_collab_game
Collaborative Reinforcement Learning on Human-Computer shared task
maze_GI_Unity
Maze Game on Unity for Human-Computer Colalboration
pytorch_tutorial
This repository contains a comprehensive tutorial designed to introduce you to the fundamental concepts and usage of the PyTorch library.
representation_learning_tutorial
Implementation of basic autoencoder architectures and SimCLRv2
stock_value_dnn
Stock value regression using DNN on fanancial data of S&P 500 companies
ANAC2015_Boulware_like_agent
A simple agent that follows Boulware-like bid policy (3rd place at domestic tournament at Technical University of Crete)
collaborative_games
RL-based human robot collaboration in shared tasks on ROS
CSE5306_Distributed_Systems_Project_1
TCP Server-Client communication for text annotation for graduate level Distributed Systems Course taught by Chance Eary at UTA during Spring 21
CSE5306_Distributed_Systems_Project_2
TCP Server-Client communication for text annotation with redundancy and polling for graduate level Distributed Systems Course taught by Chance Eary at UTA during Spring 21
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
path_planning_manhattan_distance
Path planber using manhattan distance on a known map
robot_dynamics_and_control
Dynamic Parameters Experimental System Identification and PD Controler of a single joint robot
robot_kinematics
Forward and Inverse Kinematics for simulated robot
tactile_gym
Suite of PyBullet reinforcement learning environments targeted towards using tactile data as the main form of observation.