Permits unlimited usage of the addon for commercial and non commerical releases for one single individual
Read the full license text
This plugin is built upon the Deep Q-Learning algorithm developed by Google’s DeepMind.
It enables the developer to give agents a “brain” and train them using rewards/punishments. The implementation uses convnet.js by Andrej Karpathy.
For a more detailed description of the features and abilities of the plugin, as well as an example CAPX, please see the documentation at https://www.dropbox.com/s/3lu6fuk6eucpnc7/ReinforcementLearningDocumentation.docx
Please note, the plugin comes as-is and it is not guaranteed when/that the artificial neural network will converge, nor can a certain accuracy be guaranteed.
A purchase of a Construct 2 addon permits unlimited usage for 1 single developer. This developer is permitted to use the addon for life in as many commercial and non commercial projects as they wish. The license is strictly non-transferable. If more than one developer wishes to make use of the addon, multiple licenses will be required.
Buy this item at the exclusive price today and it we will be de-listed from the Scirra store immediately!
Items with exclusive prices are not sold anywhere else, and will not be sold anywhere else ever again if purchased at this price.
This item has currently been sold an estimated 17 times to date. Buy at the exclusive price today and no one else will be able to buy it.
The Actions and Expressions, explained.
An example CAPX with a small game using Reinforcement Learning to train an agent - the comments can be useful to understand the way this plugin works.
Take a look at these other items
Ideal background melody for War.
fairytale sad loop music
Pixel Art for Platform Game
A simple Reward System for CocoonIO, Intel XDK and Desktop
Inventory & Loot for RPG
Do you best and gather as many b
20 currencies accepted here!