Path: utzoo!mnetor!uunet!husc6!bloom-beacon!gatech!purdue!decwrl!ucbvax!MITRE-BEDFORD.ARPA!bwk From: bwk@MITRE-BEDFORD.ARPA (Barry W. Kort) Newsgroups: comp.ai.digest Subject: Re: AIList V6 #87 - Queries, Causal Modeling, Texts Message-ID: <31039@linus.UUCP> Date: 6 May 88 01:12:12 GMT References:<8805051701.AA29480@ucbvax.Berkeley.EDU> Sender: daemon@ucbvax.BERKELEY.EDU Reply-To: bwk@mbunix (Barry Kort) Organization: International Teleport and Telepath, Beantown, Mass. Lines: 26 Keywords: Value System, Random Choice, Modeling, Learning, Evolution Summary: How to instill Free Will in a machine. Approved: ailist@kl.sri.com Path: utzoo!mnetor!uunet!husc6!bloom-beacon!gatech!purdue!decwrl!ucbvax!MITRE-BEDFORD.ARPA!bwk From: bwk@MITRE-BEDFORD.ARPA (Barry W. Kort) Newsgroups: comp.ai.digest Subject: Re: AIList V6 #87 - Queries, Causal Modeling, Texts Message-ID: <31039@linus.UUCP> Date: 6 May 88 01:12:12 GMT References: <8805051701.AA29480@ucbvax.Berkeley.EDU> Sender: daemon@ucbvax.BERKELEY.EDU Reply-To: bwk@mbunix (Barry Kort) Organization: International Teleport and Telepath, Beantown, Mass. Lines: 26 Keywords: Value System, Random Choice, Modeling, Learning, Evolution Summary: How to instill Free Will in a machine. Spencer Star asks: (1) What is free will for a machine? (2) Please provide a test that will determine if a machine has free will. The test should be quantitative, repeatable, and unambiguous. I suggest the following implementation of Free Will, which I believe would engender behavior indistinguishable from a sentient being with Free Will. 1) Imbue the machine with a Value System. This will enable the machine to rank by preference or utility the desirability of the anticipated outcomes of pursuing alternative courses of action. 2) Provide a random choice mechanism for selecting among equal-valued alternatives. 3) Allow the Value System to learn from experience. 4) Seed the Value System with a) the desire to survive and b) the desire to construct accurate maps of the state-of-affairs of the world and accurate models for predicting future states-of-affairs from a given state as a function of possible actions open to the machine. --Barry Kort