MinRL provides clean, minimal implementations of fundamental reinforcement learning algorithms in a customizable GridWorld environment. The project focuses on educational clarity and implementation simplicity while maintaining production-quality code standards.

Machine learning library, Distributed training, Deep learning, Reinforcement learning, Models, TensorFlow, PyTorch

Soft Actor-Critic (SAC) algorithm + Hindsight Experience Replay (HER) implementation on Robosuite Panda robot and Gymnasium Pick And Place (Pytorch)

A DRL cheat sheet for learning

Adaptive Portfolio Optimization with Multi-Agent Deep Reinforcement Learning

This project demonstrates how reinforcement learning can be used to analyze market behavior and learn automated stock trading strategies. It integrates technical analysis, data visualization, and RL algorithms to produce an intelligent trading simulation.

Master's degree thesis in Computer Science Engineering in collaboration with AIKO company

No description provided.

RL - DRL for various Environments like games and stock markets. Discover different DRL model architecture and ways to deal with RL downsides

Twin Delayed Deep Deterministic Policy Gradients (TD3) implementation on Gymnasium robotics Fetch-Reach environment (Pytorch)

A Tetris-playing bot powered by deep reinforcement learning. Experience the captivating combination of Pygame and AI as the bot showcases its mastery of Tetris.

Training Deep RL Agent for navigation and object avoidance tasks using Pytorch

Repository for my dissertation pertaining to optimal trading strategies for single-asset and multi-asset portfolios in stock markets.