T
Tim Tyler
The Matching Pennies Prize is a prize for automating machine forecasting.
The prize is currently based around languages that target the JVM -
though support for other languages is planned.
The http://matchingpennies.com/ web site will regularly hold
tournaments based on the matching pennies game, and the winners will be
awarded prizes.
The matching pennies game represents an abstract model of serial
forecasting in a simple environment partly consisting of agents with
conflicting goals.
Agents succeed by modeling the other agents and predicting their
actions.
The basic idea is to arrange things so that successful agents will
necessarily have to have solved the problem of building a powerful,
general-purpose stream compressor. This will then enable them to
implement Occam's razor, develop plausible models of the workings of
other nearby agents - and then to make successful predictions of their
actions.
I've created other material which explains the significance of
automating predictions and forecasting in more detail. Here, I will
just note that an automatic forecasting component is a key ingredient
in many machine intelligence systems.
If you put a forecasting component together with a tree-pruning
algorithm and an evaluation function, then the result is a complete
machine intelligence.
The basic idea of the prize is to allow those who are interested in
funding machine intelligence to contribute to the efforts of those who
are interested in building it.
There's an introductory video here: http://vspy.org/?v=DLaECbQujec
For more comprehensive details about The Matching Pennies Prize,
the prize fund, the award schedule, or details about how to compete
or donate please visit:
--> http://matchingpennies.com/ <--
Enjoy,
The prize is currently based around languages that target the JVM -
though support for other languages is planned.
The http://matchingpennies.com/ web site will regularly hold
tournaments based on the matching pennies game, and the winners will be
awarded prizes.
The matching pennies game represents an abstract model of serial
forecasting in a simple environment partly consisting of agents with
conflicting goals.
Agents succeed by modeling the other agents and predicting their
actions.
The basic idea is to arrange things so that successful agents will
necessarily have to have solved the problem of building a powerful,
general-purpose stream compressor. This will then enable them to
implement Occam's razor, develop plausible models of the workings of
other nearby agents - and then to make successful predictions of their
actions.
I've created other material which explains the significance of
automating predictions and forecasting in more detail. Here, I will
just note that an automatic forecasting component is a key ingredient
in many machine intelligence systems.
If you put a forecasting component together with a tree-pruning
algorithm and an evaluation function, then the result is a complete
machine intelligence.
The basic idea of the prize is to allow those who are interested in
funding machine intelligence to contribute to the efforts of those who
are interested in building it.
There's an introductory video here: http://vspy.org/?v=DLaECbQujec
For more comprehensive details about The Matching Pennies Prize,
the prize fund, the award schedule, or details about how to compete
or donate please visit:
--> http://matchingpennies.com/ <--
Enjoy,
