Using tabular and deep reinforcement learning methods to infer optimal market making strategies

Deep Q-learning (DQL) for playing Snake game

The following project concerns the development of an intelligent agent for the famous game produced by Nintendo Super Mario Bros. More in detail: the goal of this project was to design, implement and train an agent with the Q-learning reinforcement learning algorithm.

Deep Q Network and Double DQN implementation for OpenAI gym CartPole

Apply Double Deep Q Learning

Project1 Navigation

A Tetris AI using convolutional neuronal networks.

Deep RL for unsupervised hyperspectral band selection.

Play Super Mario Bros Game using Double Deep Q Network implemented in PyTorch.

Using Double Deep Q-Network to learn to play Minesweeper game

Trading Bot using Double Deep Reinfocement Learning

Reinforcement learning agent for OpenAI's Car Racing environment

This project is a Double Deep Q learning Agent that learns to play the dice game Yahtzee

Deep reinforcement learning agent

Análise de Intervenção para Ansiedade com Mediação Causal

Algorithmic Trading the Tesla Stock with Deep Reinforcement Learning. Paper:

This project trains an agent to navigate and to collect bananas in a continuous square environment. The environment is based on the Unity Machine Learning Agents Toolkit

Environment-related difference of Deep Q-Learning and Deep Double Q-Learning

Double deep q network implementation in OpenAI Gym's "Mountain Car" environment

Applying Reinforcement Learning to Solve the LunarLander-v3 Problem