An Ai using Reinforcement Learning to survive in a very basic roguelike environment

Code for the paper "DQN-based ethical decision-making for self-driving cars in unavoidable crashes: An applied ethical knob."

This code contains some modification of the main forked code and some features in order to regenerate and simulate the results mentioned in the linked paper.

Artificial Neural Network (MLP) and Deep Q-Learning Implementation from scratch, only using numpy.

Iterative Prisoner Dilemma - Tournament of 20+ classic strategies and an ML player built with DQN in Javascript

An implementation of an Autonomous Vehicle Agent in CARLA simulator, using TF-Agents

gym environnement to simulate the energetic behaviour of a real estate

DQN_cube-rubik

Amazon Fashion Product Recommendation using Deep Reinforcement Learning

Lunar Lander solved with DQN [SPANISH]

Deep Reinforcement Learning methods on Lunar Lander from OpenAI Gym.

Codes implementation of the paper "Deep reinforcement learning for minimizing tardiness in parallel machine scheduling with sequence dependent family setups"

This repository demonstrates solving a reinforcement learning challenge using the lunar lander simulation from Python's gym module, implemented with Python and TensorFlow. It offers a hands-on example of applying reinforcement learning techniques to a complex game scenario, providing insights into AI-based strategy development.

Play CartPole with DQN implemented with Tensorflow 2.0

In this repository there are the projects developed during the course of Advance Optimization-based Robot Control. The main topics are Task Space Inverse Dynamics (TSID), Differential Dynamic Programming (DDP) and Deep Q-Network (DQN).

Deep-Q-network learning algorithm to stabilize a pendulum around its upright position

Double DQN on custom environment using PyGame

Final project in ELE680 Deep Neural Networks at UiS, University of Stavanger. Comparison of DQN and Double-DQN.

Train a model with Reinforcement Learning

Comparing DQN , Double-DQN , Bootstrapped-DQN in Hungry-Geese env from kaggle