100%(1)1 out of 1 people found this document helpful
This preview shows page 6 - 8 out of 13 pages.
on RPM-inspired problems; however, we believe you can’t design an agentthat does well on RPM-inspired problems without alsoaccomplishing thoselearning goals.Is it possible to accomplish the learning goals without designing a successfulagent? Yes, which brings us to the next section...Take Chances, Make MistakesAs you’re working on these projects, you may encounter a dilemma thatstudents have reported encountering in the past. On the one hand, youmight have an idea for a way of designing your agent that you believe woulddo pretty well, but may not be all that interesting. On the other hand, youmight have an idea for a way of designing your agent that may not work atall, but would be more innovative and novel. You might hesitate to try outthis latter method because there is some risk involved: it might not work,and because your grade is based on the number of problems your agent getsright, your performance might suffer because you tried to do somethingmore interesting.If you find yourself in this dilemma, take the risk. Try out the approach youfind more innovative, novel, or interesting. If the approach ends up beingsuccessful, great! If the approach does not end up being successful,however, write about it thoroughly in your project reflection. Describe the“safe” idea that you did not use, as well as the novel idea that you did use.Explore why you believed the novel idea had potential, and try and explainwhy you believe it was not successful: were you unable to implement itsuccessfully, or was there an inherent problem in the method? How will this
experience inform your next project? How would you improve on this methodin the future?If you take a novel approach to the project and that novel approach does notpan out, we will compensate for that in your grade. In line with the learninggoals above, we wantyou to take risks and explore innovative or interestingapproaches to these problems. If you take a risk and it doesn’t pay off, yourgrade won’t suffer; just make sure to explain the risk you took in detail inyour project reflection, as well as why it didn’t pan out. In other words,demonstrate that you accomplished the learning goals of the project eventhough your agent did not perform that well.Project Difficulty and AuthenticityAs you go through these projects, you might realize as students have in thepast that they are not easy. The projects in the course are very difficult.However, they are not difficult simply for the sake of being difficult: they aredifficult because they address a real problem that the artificial intelligencecommunity is facing right now. There exists ongoing research by professors,research scientists, and PhD students right nowwith the exactsame goal asyour project here. Former KBAI students are pursuing this research inongoing Master’s theses. If the problem was easy, it wouldn’t be the subjectof ongoing research -- it would have been solved long ago.