tjwei / 2048-nn Goto Github PK
View Code? Open in Web Editor NEWThis project forked from ovolve/2048-ai
A Deep Learning AI for 2048 (2048:94.15%, 4096:78.48%, 8192: 34.5% 16384: 0.177%)
License: MIT License
This project forked from ovolve/2048-ai
A Deep Learning AI for 2048 (2048:94.15%, 4096:78.48%, 8192: 34.5% 16384: 0.177%)
License: MIT License
ImportError Traceback (most recent call last)
in ()
----> 1 from lasagne.layers.dnn import Conv2DLayer
2 from lasagne.regularization import regularize_network_params, l1, l2, regularize_layer_params_weighted
~\Anaconda3\lib\site-packages\lasagne\layers\dnn.py in ()
40 else:
41 raise ImportError(
---> 42 "requires GPU support -- see http://lasagne.readthedocs.org/en/"
43 "latest/user/installation.html#gpu-support") # pragma: no cover
44
ImportError: requires GPU support -- see http://lasagne.readthedocs.org/en/latest/user/installation.html#gpu-support
Ive downloaded the zip file, unpacked it and opened index.html with firefox.
It wont download. It only shows:
Downloading model......(about 25M).
NN AI won't work until the model is loaded
all the time
AI does not seem to work on Safari on a mac
Ive downloaded everything but I dont know how to run it, sorry if its a stupid question.
I'm assuming that when training the AI, it had only 4 outputs (north,south,east,west). Apologies if that's a faulty assumption.
For training the network, you might consider training it for a few additional outputs - not because you need them to play the game, but because by needing to provide them, the network will need an additional awareness of the game mechanics.
4 outputs (N/S/E/W) for when a move in that direction is possible, 0 if not possible.
4 outputs (N/S/E/W) for when a move in that direction will merge tiles.
1 output for a complexity score of the remaining tiles, after whatever mergers happen for the requested move.
The 'human' analog of training for these outputs would be 'learning the rules of the game' - It'll know when tiles merge and it'll know when moves are invalid, and it may internalize some of the logic for that in its decision process for moves.
I'm working on a similar project in my free time, and am curious on much info should go into the reward function, how heavy to weight certain actions or failures, etc
Hey @tjwei ! i think you may may be surprised at my score...
...isn't the max score 16384?
uhh lets make it uh... faster !! :)))
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.