The Gödel machine is often compared with Marcus Hutter's AIXI, another formal specification for an AGI. AIXI is constructed in a way its average utility converges – also through self-improvements - asymptotically to the utility of an ideal rational agent. However, different from a Gödel Machine, it usually assumes unlimited computing resources and it can never completely re-write its own code – its search code for optimizations is unmodifiable. Schmidhuber points out that the Gödel machine could start out by implementing AIXI as its initial sub-program, and self-modify after it finds a proveproof that another algorithm will be more optimal.
Schmidhuber’s design uses axiomsconsists of a solver, which attempts to systematically search for proofs that a specific re-write is useful - it will result in greater utilitysolve the goals set for the AI by more efficiently maximizing its machine, and a searcher, which has access to a set of axioms which completely describe the machine. One example design1 contains:
The searcher may completely rewrite any part of the machine, provided that it can produce a formal proof showing that such a rewrite will further the system’s goals, and that no other re-write can be proved to be more useful in a reasonable amount of time. Then, the Gödel Machine will switch its own code by the re-write. The axioms also include a detailed formal description of the machine's software and hardware, including both the components interacting with the environment and those dealing with the formal proofs, and a possibly partial description of the environment.
According to SchmidhuberSchmidhuber, this approach is globally optimal and it will not get stuck at local optimals. This is because the machine has to prove that it is not more useful to continue the proof search for alternative self-rewrites that could be more useful than the one just found.
According to Schmidhuber this approach is globally optimal and it will not get stuckedstuck at local optimals. This is because the machine has to prove that it is not more useful to continue the proof search for alternative self-rewrites that could be more useful than the one just founded.found.
The Gödel machine is often compared with Marcus Hutter's AIXI, another formal specification for an AGI. AIXI is constructed in a way its average utility converges – also through self-improvements - asymptotically to the utility of an ideal Bayesian:rational agent. However, different from a Gödel Machine, it usually assumes unlimited computing resources and it can never completely re-write its own code – its search code for optimizations is unmodifiable. Schmidhuber points out that the Gödel machine could start out by implementing AIXI as its initial sub-program, and self-modify after it finds a prove that another algorithm will be more optimal.
A Gödel machine is an approach to Artificial General Intelligence that uses a recursive self-improvement architecture proposed by Jürgen Schmidhuber. It was inspired by the mathematical theories of Kurt Gödel, where one could always find a mathematical truth or axiom that if attached to a formal system would make it stronger. A Gödel Machine is a universal problem solver that will make provably optimal self-improvements – self-improvements which can be proved to better maximize its utility.
Schmidhuber’s design uses axioms to systematically search for proofs that a specific re-write is useful - theyit will result in greater utility for the AI by more efficiently maximizing its utility function -and- and that no other re-write can be proved to be more useful in a reasonable amount of time. Then, the Gödel Machine will switch its own code by the re-write. The axioms also include a detailed formal description of the machine's software and hardware, including both the components interacting with the environment and those dealing with the formal proofs, and a possibly partial description of the environment.
The Gödel machine is often compared with Marcus Hutter's AIXI, another formal specification for an AGI. AIXI is constructed in a way its average utility converges –also– also through self-improvements-improvements - asymptotically to the utility of an ideal BayesianBayesian:rational agent. However, different from a Gödel Machine, it usually assumes unlimited computing resources and it can never completely re-write its own code – its search code for optimizations is unmodifiable. Schmidhuber points out that the Gödel machine could start out by implementing AIXI as its initial sub-program, and self-modify after it finds a prove that another algorithm will be more optimal.
A Gödel machine is an approach to Artificial General Intelligence that uses a recursive self-improvement architecture proposed by Jürgen Schmidhuber based ofSchmidhuber. It was inspired by the mathematical theories of Kurt Gödel.del, where one could always find a mathematical truth or axiom that if attached to a formal system would make it stronger. A Gödel Machine a universal problem solver that will make provably optimal self- improvements – self-improvements which can be proved to better maximize its utility.
Schmidhuber’s design uses axioms to systematically search through its own code to findfor proofs that a specific re-write is useful re-writes (which are deemed useful if- they result in greater utility for the AI).AI by more efficiently maximizing its utility function -and that no other re-write can be proved to be more useful in a reasonable amount of time. Then, the Gödel Machine will switch its own code by the re-write. The axioms also include a detailed formal description of the machine's software and hardware, including both the components interacting with the environment and those dealing with the formal proofs, and a possibly partial description of the environment.
According to Schmidhuber this approach is globally optimal.optimal and it will not get stucked at local optimals. This is because the machine has to prove that it is not more useful to continue the proof search for alternative self-rewrites.rewrites that could be more useful than the one just founded.
The Gödel machine is often compared with Marcus Hutter's AIXI. Both are, another formal specificationsspecification for an AGI. AIXI is constructed in a way its average utility converges –also through self-improvements- asymptotically to the utility of AGI.an ideal Bayesian agent. However, different from a Gödel Machine, it usually assumes unlimited computing resources and it can never completely re-write its own code – its search code for optimizations is unmodifiable. Schmidhuber points out that the Gödel machine could start out by implementing AIXI,AIXI as its initial sub-program, and self-modify after it proves suchfinds a change is beneficial.prove that another algorithm will be more optimal.
A Gödel Machinemachine is an approach to Artificial General Intelligence that uses a Recursive Self-Improvementrecursive self-improvement architecture proposed by Jürgen Schmidhuber based of the mathematical theories of Kurt Gödel.
. The axioms include a detailed formal description of the machine's software and hardware, including both the components interacting with the environment and those dealing with the formal proofs, and a possibly partial description of the environment.
According to Schmidhuber this approach is globally optimal asoptimal. This is because the search space is systematically tested in such a way the codemachine has to prove that it is not more useful to continue the proof search for alternative self-rewrites.
The Gödel machine is often compared with Marcus Hutter's AIXI. Both are formal specifications of AGI. Schmidhuber points out that the Gödel machine could start out by implementing AIXI, and self-modify after it proves such a change is beneficial.
A Gödel Machine is an approach to Artificial General Intelligence that uses a Recursive Self-Improvement architecture proposed by Jürgen Schmidhuber based of the mathematical theories of Kurt Gödel.
Schmidhuber’s design uses axioms to systematically search through its own code to find useful re-writes (which are deemed useful if they result in greater utility for the AI)
The axioms include a detailed formal description of the machine's software and hardware, including both the components interacting with the environment and those dealing with the formal proofs, and a possibly partial description of the environment.
According to Schmidhuber this approach is globally optimal as the search space is systematically tested in such a way the code has to prove that it is not useful to continue the proof search for alternative self-rewrites.
Jürgen Schmidhuber (2009) Ultimate Cognition à la Gödel. Cogn Comput (2009) 1:177–193.http://www.idsia.ch/~juergen/ultimatecognition.pdf↩