All Projects → Matesanz → Reinforcement_Learning_Course

Matesanz / Reinforcement_Learning_Course

Licence: other
Curso de Aprendizaje por Refuerzo, de 0 a 100 con notebooks y slides muy sencillas para entenderlo todo perfectamente.

Programming Languages

Dockerfile
14818 projects

Projects that are alternatives of or similar to Reinforcement Learning Course

MP-DQN
Source code for the dissertation: "Multi-Pass Deep Q-Networks for Reinforcement Learning with Parameterised Action Spaces"
Stars: ✭ 99 (+450%)
Mutual labels:  deep-reinforcement-learning
drl grasping
Deep Reinforcement Learning for Robotic Grasping from Octrees
Stars: ✭ 160 (+788.89%)
Mutual labels:  deep-reinforcement-learning
semantic-guidance
Code for our CVPR-2021 paper on Combining Semantic Guidance and Deep Reinforcement Learning For Generating Human Level Paintings.
Stars: ✭ 19 (+5.56%)
Mutual labels:  deep-reinforcement-learning
RL
Reinforcement Learning Demos
Stars: ✭ 66 (+266.67%)
Mutual labels:  deep-reinforcement-learning
DDPG
End to End Mobile Robot Navigation using DDPG (Continuous Control with Deep Reinforcement Learning) based on Tensorflow + Gazebo
Stars: ✭ 41 (+127.78%)
Mutual labels:  deep-reinforcement-learning
pokeai
Develop ultimate AI Pokémon trainer
Stars: ✭ 18 (+0%)
Mutual labels:  deep-reinforcement-learning
Carla-ppo
This repository hosts a customized PPO based agent for Carla. The goal of this project is to make it easier to interact with and experiment in Carla with reinforcement learning based agents -- this, by wrapping Carla in a gym like environment that can handle custom reward functions, custom debug output, etc.
Stars: ✭ 122 (+577.78%)
Mutual labels:  deep-reinforcement-learning
AlphaNPI
Adapting the AlphaZero algorithm to remove the need of execution traces to train NPI.
Stars: ✭ 71 (+294.44%)
Mutual labels:  deep-reinforcement-learning
datascience-mashup
In this repo I will try to gather all of the projects related to data science with clean datasets and high accuracy models to solve real world problems.
Stars: ✭ 36 (+100%)
Mutual labels:  deep-reinforcement-learning
racing dreamer
Latent Imagination Facilitates Zero-Shot Transfer in Autonomous Racing
Stars: ✭ 31 (+72.22%)
Mutual labels:  deep-reinforcement-learning
muzero
A clean implementation of MuZero and AlphaZero following the AlphaZero General framework. Train and Pit both algorithms against each other, and investigate reliability of learned MuZero MDP models.
Stars: ✭ 126 (+600%)
Mutual labels:  deep-reinforcement-learning
AI booklet CE-AUT
Booklet and exam of Artificial Intelligence Master Degree at Amirkabir University of technology.
Stars: ✭ 14 (-22.22%)
Mutual labels:  deep-reinforcement-learning
AutoPentest-DRL
AutoPentest-DRL: Automated Penetration Testing Using Deep Reinforcement Learning
Stars: ✭ 196 (+988.89%)
Mutual labels:  deep-reinforcement-learning
CrowdNav DSRNN
[ICRA 2021] Decentralized Structural-RNN for Robot Crowd Navigation with Deep Reinforcement Learning
Stars: ✭ 43 (+138.89%)
Mutual labels:  deep-reinforcement-learning
Underflow
With underflow, create trafic light clusters that interact together to regulate circulation
Stars: ✭ 12 (-33.33%)
Mutual labels:  deep-reinforcement-learning
code summarization public
source code for 'Improving automatic source code summarization via deep reinforcement learning'
Stars: ✭ 71 (+294.44%)
Mutual labels:  deep-reinforcement-learning
godpaper
🐵 An AI chess-board-game framework(by many programming languages) implementations.
Stars: ✭ 40 (+122.22%)
Mutual labels:  deep-reinforcement-learning
Smart-Traffic-Signals-in-India-using-Deep-Reinforcement-Learning-and-Advanced-Computer-Vision
We have used Deep Reinforcement Learning and Advanced Computer Vision techniques to for the creation of Smart Traffic Signals for Indian Roads. We have created the scripts for using SUMO as our environment for deploying all our RL models.
Stars: ✭ 131 (+627.78%)
Mutual labels:  deep-reinforcement-learning
Explorer
Explorer is a PyTorch reinforcement learning framework for exploring new ideas.
Stars: ✭ 54 (+200%)
Mutual labels:  deep-reinforcement-learning
rtrl
PyTorch implementation of our paper Real-Time Reinforcement Learning (NeurIPS 2019)
Stars: ✭ 57 (+216.67%)
Mutual labels:  deep-reinforcement-learning

👋 Curso sobre Reinforcement Learning

🙂 Descripción

En este curso se incluye todo lo básico relacionado con el Aprendizaje por Refuerzo. Desde los conceptos más básicos, como qué es una cadena de Markov, hasta conceptos más interesantes como la inclusión de Redes Neuronales en algoritmos de RL. Para ello, cada una de las clases cuenta con un Jupyter Notebook ejecutable con toda la teoría y con imágenes de esquemas que ayudan a una mejor comprensión. Esta pensado para que sea un curso desde 0, por ello, tanto si eres principiante, como si quieres refrescar conocimientos, este curso es para ti.

🔖 Tabla de Contenidos

Este curso está dividido en varias partes:

📜 Temas

Para ejecutar los notebooks la mejor forma es usar docker. En apenas unos minutos y sin instalar nada tendrás acceso a todos los notebooks. 🤯

0️⃣ Introducción a Reinforcement Learning

  • Agente y Entorno
  • Recompensas, Observaciones y Acciones
  • Equilibrio Exploración Explotación
  • Maximizar la Recompensa a largo plazo
  • Descubriendo Gym: Creando mi primer entorno
  • Descubriendo Gym: Creando mi primer agente

Reinforcement Learning Intro

1️⃣ Ecuación de Bellman: El valor de los estados

  • V-table: asignando un valor a cada estado
  • Ecuación de Bellman: calculando V para cada estado
  • Cálculo de la Política usando la V-table

Bellman_equation State_Value

2️⃣ Ecuación de Bellman: El valor de las acciones

  • Las acciones en los Procesos de decisión de Markov
  • Q: El valor de las acciones
  • Programación Dinámica: Iteración de Valores

Q-value

3️⃣ Q Learning

  • Diferencias Temporales: Q-learning
  • Alpha: aprender más de lo nuevo o de lo viejo
  • Gamma: cuanto más lejos en el futuro menos confianza
  • La política Óptima

Q-learning

Quick-Start: usando remote containers

1. Instala el Plugin de VSCode de Remote Containers

# Presiona Ctrl + shift + p
# Pega ext install ms-vscode-remote.remote-containers
# Presiona Enter

2. Abre el entorno de desarrollo

# Presiona Ctrl + shift + p
# Busca: Remote-Containers: Rebuild and Reopen in container
# Presiona Enter (y espera, la primera vez tarda unos minutos)

3. Abre los Notebooks

Abre el buscador y ve a http://127.0.0.1:8888/

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].