mpnunez / connect4-ai Goto Github PK
View Code? Open in Web Editor NEWTraining an AI Player to play Connect4
Training an AI Player to play Connect4
Instead of having separate files for DQN and DQN training, for example, put these together in one file/module along with the hyperparameters. In practice we can't really separate the algorithm from the agent code.
Q predicitons with MSE cost function often explode when the policy gets stuck
We don't need to record smoothed reward after each episode. Also, make sure all histograms (e.g. target network weight updates) are sampled sparsely.
Playing against this will give a much stronger player
Dueling DQN: Split Q value into the value of the state
May be easier to prototype
This way we can figure out why the agent is losing and get a better sense of its behavior.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.