PM
A few months ago I mentioned to Jim Bromer that I would build the
intelligence around the idea of opportunity. This fits directly with
the idea of goals, in a somewhat obscure way.
If you look at your candidates list below, you see part of what makes up
an opportunity. It leaves out important factors that go into choosing
which opportunity is "greatest" for the moment.
These additional factors get complicated. For example -
- how reliable are the claims of this opportunity? If we pursue this
opportunity, can we be somewhat certain we will complete the steps
needed to consummate and yield the benefit?
- what is the opportunity and how does it compare to other opportunity.
In other words, there needs to be a vocabulary of benefit and cost
that goes with consideration of any opportunity. Here is where the real
world is complex. We venture and discover many benefits that we didn't
expect. And we encounter costs that exceed our expectations. Will
there be shortages we didn't anticipate...
- where did this opportunity come from? If we want to evaluate
opportunity, we also need to consider the source. Is this simply an
idea that we cooked up according to simple logic? Is this an idea that
comes highly recommended from a reliable source - a master chef.
I understand that the ideas listed above seem off-base from looking at
goals, but the real world "intelligent" doesn't work via figuring
everything out. It works from suggestion and observation of what works
and how it worked out. The intelligence that we want to embody will one
day need to be able to choose between opportunity rather than simply
follow "sub-goals" that make up a recipe.
To get this intelligence going, build the database of opportunity.
Stan
(sorry if I missed a relevant prior post, I'm way behind in list reading
- busy time of year... yade yada .)
On 06/11/2012 06:31 PM, Piaget Modeler wrote:
Abram, you've characterized it properly. In my vernacular subgoals = goals.
I would say that the job of this particular attention module is to
reprioritize the open goal set,
given all available information.
So the question for me is what should all available information consist of?
Some candidates are: (1) The current context, for sure, (2) alerts, (3)
expectation failures and mismatches,
(4) past prioritizations, (5) past episodes.
Anything else?
Your thoughts?
Date: Mon, 11 Jun 2012 11:11:58 -0700
Subject: Re: [agi] Attention
From: [email protected]
To: [email protected]
PM,
OK. So, in this case, the goal selector is clearly selecting subgoals to
prioritize.
It's a difficult question which needs a quickly computable answer, so
the system needs to somehow gather information over time which tells it
what subgoals have been most useful in the past, in what situations.
This process can use a wide variety of information; essentially
anything. However, to make an efficient choice, the information
considered at any particular time needs to be narrowed down somehow. The
space of possible sub-goals is also potentially difficult, and needs to
be narrowed down heuristically...
Perhaps the best that I can say at the moment is, this seems like the
sort of problem which requires empirical testing to see what works and
what doesn't!
--Abram
On Fri, Jun 8, 2012 at 5:49 PM, Piaget Modeler
<[email protected] <mailto:[email protected]>> wrote:
Ben
Yours is a sufficient response. Thank you.
Abram
Suppose we decompose a cognitive system down into a few components:
1. A planner (which is fed a goal, a current state and a set of
possible actions (i.e., operators, methods, cases, etc.)),
2. An action selector (which is fed the current state, a prioritized
set of goals, and a set of methods to choose from),
3. A goal selector / Attention module whose job is to prioritize or
select goals for the cognitive system.
My question was what would you feed the goal selector to ensure it
did its job (prioritizing goals) properly?
In a paper I read recently "A Case Study of Goal-Driven Autonomy in
Domination Games" by Hector Munoz-Avila and David W. Aha
the authors, in their CB-gda system, decompose the cognitive system
into two case-based components (a) a planning component,
and (b) a mismatch goal [selection] component. The purpose of the
latter component was to correct for errors encountered by the
planner. The input for the mismatch goal selection component is a
mismatch (the difference between the expected state and the
goal state).
Q: What else would be relevant input for a goal selector / Attention
component?
Date: Fri, 8 Jun 2012 17:49:15 -0400
Subject: Re: [agi] Attention
From: [email protected] <mailto:[email protected]>
To: [email protected] <mailto:[email protected]>
In the OpenCog framework, we supply some hard-coded "top level
goals", and then the system learns how to achieve these, which may
include learning subgoals...
The top level goals are generally of the form "keep so-and-such
parameter within range [L,R]"
Experience of novelty and discovery of new things are good general
top-level goals. For an character in a virtual 3D environment, we
add in stuff like getting energy (e.g. from batteries or food),
staying safe, and partaking in social interaction....
In reference to this sort of framework, I'm unsure if you're talking
about top-level goals or learned subgoals...
-- Ben G
*AGI* | Archives <https://www.listbox.com/member/archive/303/=now>
<https://www.listbox.com/member/archive/rss/303/7190161-766c6f07> |
Modify <https://www.listbox.com/member/?&;> Your Subscription
[Powered by Listbox] <http://www.listbox.com>
--
Abram Demski
http://lo-tho.blogspot.com/
*AGI* | Archives <https://www.listbox.com/member/archive/303/=now>
<https://www.listbox.com/member/archive/rss/303/19999924-5cfde295> |
Modify <https://www.listbox.com/member/?&;> Your Subscription [Powered
by Listbox] <http://www.listbox.com>
*AGI* | Archives <https://www.listbox.com/member/archive/303/=now>
<https://www.listbox.com/member/archive/rss/303/9320387-ea529a81> |
Modify
<https://www.listbox.com/member/?&;>
Your Subscription [Powered by Listbox] <http://www.listbox.com>
-------------------------------------------
AGI
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-c97d2393
Modify Your Subscription:
https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-2484a968
Powered by Listbox: http://www.listbox.com
