python code accompanying the talk "Reinforcement Learning, An Introduction", Dr. Sven Mika (Duesseldorf, Germany Aug 20th 2017)

A novel A3C-based architecture for crawling in Rogue's dungeons with Deep Reinforcement Learning

A smart agent which solves a escaping maze using MDP

lrl: Learn Reinforcement Learning - A package to help people learn basic planning and Reinforcement Learning

This repo will contain Implementations of different RL algorithms, worked examples and requests for research from OpenAI.

Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.

UofT COVID-19 Engagement Project

Reinforcement learning using a genetic algorithm to train a neural network to play a version of the classic game Breakout

QLearning project for the Artificial Intelicence class using Python

Repository for the course project done as part of CS-747 (Foundations of Intelligent & Learning Agents) course at IIT Bombay in Autumn 2022.

Reinforcement Learning

A small application applying the QLearning algorithm to the TicTacToe game

A simple header only template library for reinforcement learning algorithms

ResPic is an image classification project that utilizes the power of a pre-trained ResNet50 model for accurate and efficient image classification.

I created different real worl project by using reinforcement learning

This repository hosts the code and resources for a comprehensive study on optimizing greenhouse conditions using Reinforcement Learning algorithms such as PPO, A2C, and SAC. For detailed results, explanation of the environments, and the algorithms, please refer to the accompanying report.

Reinforcemenet Learning game of tag with 2 autonomous agents in a 2D environment. The game generation begins with a "tagger" agent whose goal is to tag the other agent, and a second "escaper" agent whose goal is to escape this tagger. The generation ends after either the tagger agent touches the escaper (in which case the tagger wins), or after …