reinforcement learning

This project was an attempt to reproduce the work published by DeepMind for the paper https://arxiv.org/pdf/1707.06600.pdf . This reproduction was part of the course INFO-F409 : Learning Dynamics.

C++ high-performance gym environment framework

Imitating the behavior of Gamette players in their supply chain decisions.

Reinforcement Learning (Artificial Intelligence) Algorithm for solving OpenCV problem

Part of the code experimets related to this publication: https://www.sciencedirect.com/science/article/pii/B9780128186343501545

Multi-agent implementations of Reinforcement Learning algorithm Proximal Policy Optimization.

Minigrid is a simulation of the world in the form of a grid. The target is to train an agent to understand textual instructions.

Using reinforcement learning methods (Monte-Carlo algorithm) to create an AI in tic-tac-toe

An attempt at developing a learning agent to train an enemy mob in a mario like game

A Keras-RL based DQL agent that can learn to play pong.

This project aims is to learn adaptive parameter updates of nonlinear programming solvers by using reinforcement learning techniques.

A simple harbour simulation to test multi-agent reinforcement learning algorithms based on multi-agent-particle-envs from OpenAi

Machine Learning (ML) algorithm for the resource allocation problems in the Low Power Wide Area Network (LPWAN).