tag:blogger.com,1999:blog-7487967624215307336.post4336160754630712881..comments2024-03-14T07:58:37.839+01:00Comments on Marek Rosa - dev blog: First round of General AI Challenge just launched: Gradual Learning – Learning like a HumanMarek Rosahttp://www.blogger.com/profile/02675819792454369037noreply@blogger.comBlogger15125tag:blogger.com,1999:blog-7487967624215307336.post-60785589782638551372017-04-07T02:06:27.289+02:002017-04-07T02:06:27.289+02:00Just don't do it... Cybernet...Just don't do it... Cybernet...Marcos Ossehttps://www.blogger.com/profile/06902743054962915809noreply@blogger.comtag:blogger.com,1999:blog-7487967624215307336.post-30227356349862190062017-03-10T18:42:46.922+01:002017-03-10T18:42:46.922+01:00Thanks Frank! This is great!Thanks Frank! This is great!Marek Rosahttps://www.blogger.com/profile/16960832628849493781noreply@blogger.comtag:blogger.com,1999:blog-7487967624215307336.post-71483669410582125592017-03-10T04:57:16.318+01:002017-03-10T04:57:16.318+01:00I wrote a simple webserver, so that humans can try...I wrote a simple webserver, so that humans can try to solve the tasks without the need to install Python etc.<br />http://www.frank-buss.de/ai/index.html<br />Feel free to use it for whatever you like, commit it to the github repository, or even better: enhance it with some logging and then install it on the challenge website, with a statistics page, how many tasks humans can solve.Frank Busshttps://www.blogger.com/profile/05428955941834094270noreply@blogger.comtag:blogger.com,1999:blog-7487967624215307336.post-36921784010096406612017-03-07T17:23:44.826+01:002017-03-07T17:23:44.826+01:00Hi Frank,
in the blocksworld example, we definitel...Hi Frank,<br />in the blocksworld example, we definitely would not want you to perform complex planning; that seems out of the scope. However, parsing and answering simple questions plus maintaining state about the environment seems viable; after all, the micro-tasks in the public curriculum use these concepts. Notice that the micro-tasks teach the agent even some basics of boolean logic (and, or).<br /><br />We're actually hoping for the corrolary you write about :-) I mean - your AI capable of solving the public curriculum or your own curriculum will be flexible enough so that it can also solve the evaluation curriculum. <br /><br />I completely agree with you that developing the right curriculum is half of the problem and takes a lot of time. We currently don't have curricula that would lead to the example mini-tasks 1.6.1.1 and 1.6.1.2. If we find the time to do so, we could try to create those too, but I don't want to make any promises now. What I can promise is that we'll do our best to make the evaluation curriculum really gradual and the tasks within to advance by small steps at a time.<br /><br />We tested our curriculum on human solvers. Some did not get through the initial tasks, some did (the more advanced tasks are actually easier for humans because of our biases). But none of the tasks remained unsolved. So in principle, we believe the tasks are solvable and we hope that they will also solvable by AIs from the challenge. I agree with your intuition about learning by example or by feedback from the teacher - the advanced tasks in the public curriculum go in this direction. We wanted to see an AI that will be able to discover this principle of gathering feedback from the input without its creators explicitly telling it about the format of the feedback or its location.<br /><br />About your last question, there are no consolation prizes, but next to the objective (quantitative) prize there is the subjective (qualitative) prize, which is evaluated by a jury and where the best idea (and not necessarily code) wins. So don't give up hope :-)Martin Poliakhttp://www.goodai.comnoreply@blogger.comtag:blogger.com,1999:blog-7487967624215307336.post-60508819008436339152017-03-06T20:42:53.604+01:002017-03-06T20:42:53.604+01:00Hi Martin,
thanks, I'm new to AI programming ...Hi Martin,<br /><br />thanks, I'm new to AI programming and didn't know the "box worlds" specification. I thought it would be more complicated, like visualizing 3D blocks on a real table. So in your challenge it would be something like described here: http://www.cs.umd.edu/~nau/papers/gupta1992complexity.pdf And I guess only EBW, and not VBW, LBW or VLBW? This would be easier.<br /><br />But I still don't see how this could be teached with micro-tasks only, without hard-coding some fundamental features into the AI, like boolean logic, or an expression parser, or even a concept of number. Maybe it will be possible, by carefully designing a lot of micro-tasks, but I have no idea how they would look like to solve the A.1.6.1.1 and A.1.6.2.1 hardtest tasks, and what fundamental capabilities would need to be hard-coded, because it can't be thought with micro-tasks. So it might be impossible to train such concepts as "parsing hex numbers", "add two numbers" or "declare a variable" with micro-tasks, only. Which means it is just luck if the AI knows already the required concepts (hard-coded) to solve the non-public mini-tasks.<br /><br />Of course, the corollary might be also true: If I manage to create a set of micro-tasks, and program an AI which don't know the concept of "hex number parsing", or "adding" as hard-coded parts of the AI in advance, but it can learn it with my sets of micro-tasks, then this AI might be able to solve other complex mini-tasks as well, like the blocks world task. But this depends highly on the set of micro-tasks and the details of the AI. I would even expect developing a set of micro-tasks which can teach an AI to solve a given mini-task, will be more difficult than developing the AI itself. Could you provide a set of micro-tasks, which can teach an AI to solve the example mini-tasks in A.1.6.1.1 and A.1.6.2?<br /><br />Even some of the micro-tasks might be too difficult. I read the examples in the challenge specifications and some look too contrived. There are just too many possible rules, and contradictions, that an AI (or even a human) can possibly learn this with the one-bit reward output, and in the time defined by the challenge. I tried the first simplest task from the Python example (in human-interactive-mode), which uses a random 10 chars alphabet and the rule is that you have to respond with one randomly (at start) chosen char. Shame on my, I couldn't solve this, but it was immediately clear after I saw the Python code (yes, I'm a programmer, not a mathematician). I think the most efficient way for an AI (and humans) to learn is by example, or at least by providing definitions or axioms, and by asking questions back from the teacher, or asking nature (doing physical experiments). The micro-tasks are like looking for a needle in a universe-size haystack, especially if you consider the required micro-tasks to learn fundamental concepts like "parsing a hex number". In summary, I don't think this is the right approach to develop an AI and might even not work at all.<br /><br />Might be still fun to try this, even if nobody manages to win the challenge. Do you plan to give consolation prizes? :-)Frank Busshttps://www.blogger.com/profile/05428955941834094270noreply@blogger.comtag:blogger.com,1999:blog-7487967624215307336.post-77005031229704963402017-03-06T17:19:56.193+01:002017-03-06T17:19:56.193+01:00Hi Frank,
the examples in A.1.6 use simplified la...Hi Frank, <br />the examples in A.1.6 use simplified language constructs that require simpler than NLP processing. For example, one could imagine a system with language processing capabilities on the level of an LL or LR parser for processing the examples. Sure, such a system is still difficult for the current state of AI. But we intend to help the AI by guiding its learning process. We will first teach it to solve simpler parsing tasks before asking it solve these hardest-level tasks.Martin Poliakhttp://www.goodai.comnoreply@blogger.comtag:blogger.com,1999:blog-7487967624215307336.post-48392201172671458402017-03-05T01:42:37.053+01:002017-03-05T01:42:37.053+01:00Could you clarify the specification about the non-...Could you clarify the specification about the non-public tasks? In https://mirror.general-ai-challenge.org/challenge_first_round_specifications.pdf you say that natural language processing is not necessary for solving the tasks (page 13). But then it says that the tasks in A.1.6 are examples what could be used for the non-public tasks, and these tasks includes parsing "evaluate" for calculating formulas, and other simplified language constructs, like "good if", and even some examples from "Blocks World". So in my understanding you could design any task, like playing the Tetris game with (simple) English words. This seems to be too difficult for the current state of AI and I predict that nobody can manage to write a program which solves all tasks.Frank Busshttps://www.blogger.com/profile/05428955941834094270noreply@blogger.comtag:blogger.com,1999:blog-7487967624215307336.post-71690565383114323642017-02-22T08:48:42.754+01:002017-02-22T08:48:42.754+01:00I think efficient pattern-detection is the core. M...I think efficient pattern-detection is the core. Music, Text/Syntax patterns, outlines in visual changes.<br />An example of pattern-detection is: W-ORT / WORD (matches (W+)(ort/place) with (wort/word) by using a different language) and then can link "place" to NOUN→"noun" for sentence construction because word→"noun".<br /><br />After that, I would try a pathfinder-approach (start-word to destination-word over context).<br />This pathfinder uses a context and splits 50% into brute force and 50% intuition (linking a context to a similar context).<br /><br />Using regex functions is nice, because it's language-independent (java, c, everything implements regex) and I hope I can expand on that in StarMade https://starmadedock.net/threads/regai-blueprinting-regex-ais.28430/Anonymoushttps://www.blogger.com/profile/07566674998000764184noreply@blogger.comtag:blogger.com,1999:blog-7487967624215307336.post-57829791786868999512017-02-17T13:14:46.896+01:002017-02-17T13:14:46.896+01:00Thanks for the heads up.
GoodAI won't have exc...Thanks for the heads up.<br />GoodAI won't have exclusivity on the submitted solution(s). All participants have the right to share it however they want, and it would be very hard to actually claim that GoodAI invented the solution if the author has already published it somewhere else. Also, the evaluation tasks will be published after the one month evaluation period ends. So everyone will get reassurance on the competitions transparency.George Mamakosnoreply@blogger.comtag:blogger.com,1999:blog-7487967624215307336.post-44012216747019434822017-02-17T11:18:43.481+01:002017-02-17T11:18:43.481+01:00Hi, I am developer in KeenSWH. Please, contact us ...Hi, I am developer in KeenSWH. Please, contact us on support@keenswh.com and we will solve your issue.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-7487967624215307336.post-14401172661707757862017-02-17T01:05:42.166+01:002017-02-17T01:05:42.166+01:00The "General AI Challenge" is too confin...The "General AI Challenge" is too confining for me to work within its framework. Therefore, while the Challenge is moving forward, I will be designing and coding Artificial General Intelligence on a divergent pathway. Mentifexhttp://medium.com/p/5d6cfd644661noreply@blogger.comtag:blogger.com,1999:blog-7487967624215307336.post-31069012042406542862017-02-16T21:40:24.357+01:002017-02-16T21:40:24.357+01:00There might be a slight confusion with this compet...There might be a slight confusion with this competition - namely, when a successful solution is created and applied for the competition, the creator would send away his work without any guarantee that the company won't claim the work as their own and take credit for it, never actually rewarding the creator... Or maybe telling the public the goal hasn't been reached, therefore "repeating" the competition, while in fact the successful product will be kept and used?<br /><br />Is there any guarantee against this? It would definitely encourage more independent creators as they would be reassured their work wouldn't be stolen.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-7487967624215307336.post-58792435265241528352017-02-16T19:29:48.288+01:002017-02-16T19:29:48.288+01:00That's great, but hundreds of SE players can&#...That's great, but hundreds of SE players can't play SE second week in a row, coz one of programmers made a buggy "drivers update" warning. But they released lens flares instead of simple fix...Kirillhttps://www.blogger.com/profile/14455885875319530126noreply@blogger.comtag:blogger.com,1999:blog-7487967624215307336.post-53855202913451303442017-02-16T10:12:26.771+01:002017-02-16T10:12:26.771+01:00ThanksThanksMarek Rosahttps://www.blogger.com/profile/16960832628849493781noreply@blogger.comtag:blogger.com,1999:blog-7487967624215307336.post-35121134783236101262017-02-16T02:32:44.707+01:002017-02-16T02:32:44.707+01:00I can see you guys finally started appreciate the ...I can see you guys finally started appreciate the difficulties of AGI. There are no more forums on your web-sites, however, remember what I was trying to tell you before. I can see, you are still trying to follow "all good methodologies".<br /><br />It is hard to tell something since judging from the first step indicates very problematic base of an AGI approach. Simply speaking I don’t think you can create a gradual AGI agent with its learning environment. This would be equivalent to the definition of an incremental intelligence. Not to mention the difficulties of scaling this type of approach.<br /><br />In brief: designing "an agent that understands" could be viewed as solving the AGI in itself. This would require much much more to even begin with.<br /><br />If you guys are really serious about AGI try to see the big picture and how all this fit in general. Hope you guys have a lot of fun learning all this stuff, and won’t be discouraged by local minima.<br /><br />It is always refreshing to read about people/companies genuinely interested in the AGI field.<br /><br />Anyway, best wishes and keep your mind open<br /><br />focus2000x<br />Anonymousnoreply@blogger.com