GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → navjindervirdee → 2048 Deep Reinforcement Learning

navjindervirdee / 2048 Deep Reinforcement Learning

Licence: mit
Trained A Convolutional Neural Network To Play 2048 using Deep-Reinforcement Learning

Labels

jupyter-notebookneural-networkreinforcement-learningconvolutional-neural-networksdeep-reinforcement-learningq-learningdeep-q-network

Projects that are alternatives of or similar to 2048 Deep Reinforcement Learning

Hands On Reinforcement Learning With Python
Master Reinforcement and Deep Reinforcement Learning using OpenAI Gym and TensorFlow
Stars: ✭ 640 (+278.7%)
Mutual labels:  jupyter-notebook, reinforcement-learning, deep-reinforcement-learning, q-learning, deep-q-network
Rad
RAD: Reinforcement Learning with Augmented Data
Stars: ✭ 268 (+58.58%)
Mutual labels:  jupyter-notebook, reinforcement-learning, deep-reinforcement-learning, deep-q-network
Rl Course Experiments
Stars: ✭ 73 (-56.8%)
Mutual labels:  jupyter-notebook, reinforcement-learning, deep-reinforcement-learning, deep-q-network
Reinforcement learning tutorial with demo
Reinforcement Learning Tutorial with Demo: DP (Policy and Value Iteration), Monte Carlo, TD Learning (SARSA, QLearning), Function Approximation, Policy Gradient, DQN, Imitation, Meta Learning, Papers, Courses, etc..
Stars: ✭ 442 (+161.54%)
Mutual labels:  jupyter-notebook, reinforcement-learning, deep-reinforcement-learning, q-learning
Deeprl Tutorials
Contains high quality implementations of Deep Reinforcement Learning algorithms written in PyTorch
Stars: ✭ 748 (+342.6%)
Mutual labels:  jupyter-notebook, reinforcement-learning, deep-reinforcement-learning, deep-q-network
Accel Brain Code
The purpose of this repository is to make prototypes as case study in the context of proof of concept(PoC) and research and development(R&D) that I have written in my website. The main research topics are Auto-Encoders in relation to the representation learning, the statistical machine learning for energy-based models, adversarial generation networks(GANs), Deep Reinforcement Learning such as Deep Q-Networks, semi-supervised learning, and neural network language model for natural language processing.
Stars: ✭ 166 (-1.78%)
Mutual labels:  reinforcement-learning, deep-reinforcement-learning, q-learning, deep-q-network
Reinforcement Learning With Tensorflow
Simple Reinforcement learning tutorials, 莫烦Python 中文AI教学
Stars: ✭ 6,948 (+4011.24%)
Mutual labels:  reinforcement-learning, q-learning, deep-q-network
Basic reinforcement learning
An introductory series to Reinforcement Learning (RL) with comprehensive step-by-step tutorials.
Stars: ✭ 826 (+388.76%)
Mutual labels:  jupyter-notebook, reinforcement-learning, q-learning
Async Deeprl
Playing Atari games with TensorFlow implementation of Asynchronous Deep Q-Learning
Stars: ✭ 44 (-73.96%)
Mutual labels:  reinforcement-learning, deep-reinforcement-learning, q-learning
Ml In Tf
Get started with Machine Learning in TensorFlow with a selection of good reads and implemented examples!
Stars: ✭ 45 (-73.37%)
Mutual labels:  reinforcement-learning, convolutional-neural-networks, deep-reinforcement-learning
Notebooks
Some notebooks
Stars: ✭ 53 (-68.64%)
Mutual labels:  jupyter-notebook, reinforcement-learning, q-learning
Gym Fx
Forex trading simulator environment for OpenAI Gym, observations contain the order status, performance and timeseries loaded from a CSV file containing rates and indicators. Work In Progress
Stars: ✭ 151 (-10.65%)
Mutual labels:  reinforcement-learning, q-learning, deep-q-network
Tensorflow Tutorial
TensorFlow and Deep Learning Tutorials
Stars: ✭ 748 (+342.6%)
Mutual labels:  reinforcement-learning, convolutional-neural-networks, deep-reinforcement-learning
Deep Q Learning
Minimal Deep Q Learning (DQN & DDQN) implementations in Keras
Stars: ✭ 1,013 (+499.41%)
Mutual labels:  reinforcement-learning, deep-reinforcement-learning, deep-q-network
Pysc2 Examples
StarCraft II - pysc2 Deep Reinforcement Learning Examples
Stars: ✭ 722 (+327.22%)
Mutual labels:  reinforcement-learning, deep-reinforcement-learning, deep-q-network
Reinforcementlearning Atarigame
Pytorch LSTM RNN for reinforcement learning to play Atari games from OpenAI Universe. We also use Google Deep Mind's Asynchronous Advantage Actor-Critic (A3C) Algorithm. This is much superior and efficient than DQN and obsoletes it. Can play on many games
Stars: ✭ 118 (-30.18%)
Mutual labels:  jupyter-notebook, reinforcement-learning, deep-reinforcement-learning
Ctc Executioner
Master Thesis: Limit order placement with Reinforcement Learning
Stars: ✭ 112 (-33.73%)
Mutual labels:  jupyter-notebook, reinforcement-learning, q-learning
Advanced Deep Learning And Reinforcement Learning Deepmind
🎮 Advanced Deep Learning and Reinforcement Learning at UCL & DeepMind | YouTube videos 👉
Stars: ✭ 121 (-28.4%)
Mutual labels:  jupyter-notebook, reinforcement-learning, deep-reinforcement-learning
Tensorflow Book
Accompanying source code for Machine Learning with TensorFlow. Refer to the book for step-by-step explanations.
Stars: ✭ 4,448 (+2531.95%)
Mutual labels:  jupyter-notebook, reinforcement-learning, convolutional-neural-networks
Dissecting Reinforcement Learning
Python code, PDFs and resources for the series of posts on Reinforcement Learning which I published on my personal blog
Stars: ✭ 512 (+202.96%)
Mutual labels:  reinforcement-learning, deep-reinforcement-learning, q-learning
View All Similar Projects ➔

Trained A Neural Network To Play 2048 using Deep-Reinforcement Learning

Watch the Network Playing 2048!

2048 Game

2048 is a single-player sliding block puzzle game designed by Italian web developer Gabriele Cirulli. The game's objective is to slide numbered tiles on a grid to combine them to create a tile with the number 2048; however, you can keep playing the game, creating tiles with larger numbers.

2048 is played on a gray 4×4 grid, with numbered tiles that slide smoothly when a player moves them using the four arrow keys.Every turn, a new tile will randomly appear in an empty spot on the board with a value of either 2 or 4. Tiles slide as far as possible in the chosen direction until they are stopped by either another tile or the edge of the grid. If two tiles of the same number collide while moving, they will merge into a tile with the total value of the two tiles that collided. The resulting tile cannot merge with another tile again in the same move. Higher-scoring tiles emit a soft glow.

A scoreboard on the upper-right keeps track of the user's score. The user's score starts at zero, and is incremented whenever two tiles combine, by the value of the new tile. As with many arcade games, the user's best score is shown alongside the current score.

The game is won when a tile with a value of 2048 appears on the board, hence the name of the game. After reaching the 2048 tile, players can continue to play (beyond the 2048 tile) to reach higher scores. When the player has no legal moves (there are no empty spaces and no adjacent tiles with the same value), the game ends.

Reinforcement Learning

Reinforcement learning (RL) is an area of machine learning inspired by behaviourist psychology, concerned with how software agents ought to take actions in an environment so as to maximize some notion of cumulative reward. The problem, due to its generality, is studied in many other disciplines, such as game theory, control theory, operations research, information theory, simulation-based optimization, multi-agent systems, swarm intelligence, statistics and genetic algorithms. In the operations research and control literature, reinforcement learning is called approximate dynamic programming, or neuro-dynamic programming. The problems of interest in reinforcement learning have also been studied in the theory of optimal control, which is concerned mostly with the existence and characterization of optimal solutions, and algorithms for their exact computation, and less with learning or approximation, particularly in the absence of a mathematical model of the environment. In economics and game theory, reinforcement learning may be used to explain how equilibrium may arise under bounded rationality.

Network Architecture

Activation Function and Optimizer

  • Activation - RELU
  • Optimizer - RMSPRop

Deep Learning Framework

  • Tensorflow

Loss Graph

  • Y-AXIS = Avg Loss of 50 games
  • X-AXIS = Number of Episodes

Scores Graph

  • Max Tile Reached = 4096

  • MAX Score Reached = 59724

  • Y-AXIS = Avg Score of the 50 games

  • X-AXIS = Number of Episodes

Game Outcome:

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].