Our Trip Planning Robot Overlords
created by a machine
While I was testing our touring plan software in Walt Disney World last week, a computer named AlphaGo was beating one of the world’s best players of a game called Go. What made it remarkable is that Go is an enormously complicated game – there are something like 10^170 possible moves (that’s a 1 followed by 170 0’s). And that gave me the idea to express, in terms of games, how complicated it is to create an efficient theme park touring plan, and why we think computers can help.
The chart below shows some common games, an estimate of how many different ways there are to play that game, and what that complexity is similar to in terms of Magic Kingdom rides. For example, there are just under 32,000 ways to play the game tic-tac-toe. That’s in the same ballpark as the 40,320 ways to ride 8 attractions in the Magic Kingdom.
| Game | Ways to Play | Like a Touring Plan with |
| Tic-Tac-Toe | 31,896 | 8 attractions |
| Connect 4 | 4.5 x 10^12 | 15-16 attractions |
| Checkers | 5 x 10^20 | 21-22 attractions |
| Chess | 10^40 to 10^50 | 35-42 attractions |
| Go | 10^170 | 106 attractions |
For comparison, our 1-Day Magic Kingdom Touring Plan for Adults has 26 steps, including lunch and dinner. Finding a good touring plan for that is “only” about 370,000 times more complicated than finding a good way to play checkers. I’ve helped write a fair number of books about getting the most out of your day at a theme park. But no book, no matter how good, can give you enough tips, tricks, and rules to sort through that kind of complexity. Put another way: Do I think I could beat a computer at checkers after reading one book on it? No. I might not make some common, rookie mistakes, but I won’t do well.
You’re probably thinking: Sure, there are a bajillion possible combinations of Magic Kingdom rides, but I can eliminate most of them pretty easily – don’t visit Country Bear Jamboree first, for example. But that’s misleading for a few reasons. For one thing, there plenty of scenarios – like touring plans that begin around noon – in which visiting Country Bear Jamboree would probably be a good idea.
Another is that people are generally bad at considering unorthodox strategies such as riding Country Bears first, even if they end up being good ideas. In the Go game referenced above, the computer’s 19th move was completely unexpected not only by the expert it was playing against, but by millions of Go players watching the match. It turned out to be a good move by the computer (it won the game) but widely acknowledged as a something no human would have done.
You might be tempted to say that all computer programs (ours included) have errors in their logic. Ask any parent of a teenager (ours included) whether people act logically all the time. The advantage to putting our touring plan software online (and free!) is that we’re able to get feedback if something looks amiss. We’re coming up on 11 million computer-optimized touring plans, and a person has looked at every one of them. Sometimes we get reports of things that are actual bugs; most of the time it’s that the computer has found an uncommon strategy.
A few other things add to the complexity of making a good touring plan: rides break down, the right FastPasses aren’t always available, and people run late. When a ride breaks down, it’s like a game referee telling you that you can’t make a move you thought you could make. Whatever strategy you had followed to that point, suddenly isn’t allowed. During my day at the Magic Kingdom last week, for example, 3 rides were temporarily closed when I attempted to ride them. A book can’t prepare for those kinds of events.
It’s the same with FastPasses – in our Unofficial Guide touring plan, we tell you to get morning FastPasses for Seven Dwarfs Mine Train, Big Thunder Mountain, and Peter Pan’s Flight. But those weren’t available by the time I made my plan, so the book’s strategy no longer made sense. And while I got to the park 45 minutes early, as the book suggested, that’s not always possible. People run late all the time, for lots of reason. In our game analogy, running late is like losing a turn. That calls for changing your strategy on the fly, in a few minutes, under less than ideal conditions. (I just clicked the “Optimize” button on the app.)
The last thing I’ll say is that having computers be better at games has actually improved how well people play games. In everything from poker to chess, the best human players improve their own games by playing against machines. The experts get to try hundreds of different, new strategies, while seeing what the computer does at the same time. It’s probably the same with touring plans – it doesn’t hurt to see what the computer would do in the same situation.
You May Also Like...
-
Sometimes it is fun to just take it all in while you're at Walt Disney World. Recently, we spent an afternoon…
-
It's always a magical time when we visit Magic Kingdom. This weekend, our team arrived early to enjoy a morning at…
-
One of the most popular special activities that people take advantage when visiting Walt Disney World is the Disney Early Morning…
-
Walt Disney World is typically seen as a vacation that must be planned months, if not years, in advance. There are…
Can’t thank you enough for all your hard work! These touring plans make a huge difference to our planning!
I have a specific question about the crowd calendar. We will be visiting Disney from Canada. Our Christmas break this year runs from December 24th to January 9th (much later than usual). The crowd calendar is showing January 3rd to 9th, 2017 as having decently low crowds. Doing some quick searching online it seems like based on where Christmas falls this year, about half of school boards seemed to pick the week of Christmas and the week BEFORE Christmas for their holidays and half the boards seemed to pick the week of Christmas and the week AFTER Christmas for their holidays. I’m wondering if some schools having the first week of January off has already been incorporated into the crowd calendar, or if I’m going to see a big change to crowd predictions for the first week of January 2017 in the future?
I don’t want to get too far planning for that week if crowds are really going to be crazy with lots of kids still on holidays!
Thanks again for all your hard work!
We went from 12/31-1/10 this year and it was pretty good. I would recommend it.
Hi Len,
Great article as always! Since we’re talking about enhancement, is there a way to add a frequent potty break button? Last time I went to the World it was with 2 small kids and 2 seniors. We lost a lot of time looking for restrooms when, if we had planned it, we could have gone when the plan said we’d be passing one. Or at least have a break every two hours or so. It really threw us off plan by the end of the day…
Thanks,
Ali
Thanks! Let me see what we can do, Ali. How much time do you think we should allocate for those breaks?
Maybe 10-15 minutes? Enough time to find a restroom and use it. If you end up not using one of your designated breaks for that call of nature, it could also be used for a snack time.
I know smokers are the scourge of WDW, but being able to add “Smoke Break” into the plan would be so helpful. There are 4 smoking areas in MK, but 2 of those are more centrally located & used more frequently.
It would be great if the plan considers optimum tour pattern for all the parks with a few smoke breaks.
Len, great post. Very useful info to consider. I’ve been using your plans for years now and if I can be selfish, I hope nobody else finds out about them so I can keep ahead of everyone else. On a serious note, I do have a touring question. What happens when you get to a step in your plan and the wait is much greater than expected in the plan? What I’ve done in the past is this, before entering the queue I’d re-optimize and go from there even it that means skipping the ride that I am standing outside of. Is this how the software is intended to be used?
Thanks Matt!
Yeah, that’s what I’d do: re-optimize and see what the app suggests. If the wait has been higher than expected for more than 5 minutes, our day-of wait times should be adjusted automatically, and the new plan would take that higher wait into account.
You might be able to help that process along by entering the posted wait time into Lines first, then re-optimizing. Like I said, it shouldn’t take more than 5 minutes to update our predictions for the rest of the day.
I can’t even imagine how complicated it is to add features to touring plans but something I’d like is being able to pin something so it won’t move when optimizing. (Keeping a particular favorite first for a preschooler, keeping pirate adventures after dark, or keeping a FPP choice even if the optimizer thinks it’s a bad choice)
Any hope for this in the future? Still love touring plans and even my non-Disney husband appreciates how much more we can accomplish with them.
Thanks Sandra! Yes, we can work on keeping your FPP choices even if the optimizer thinks it’s a bad idea. I spoke with one of our developers today and it should be done in a couple of weeks.
We have the “pin something” idea in our list of things to do, too. Hasn’t yet bubbled to the surface, but if enough people ask for it, we can do it. I’ll keep an eye out for more requests. Thanks again!
I would love to see a “pin it” type feature. There’s certain attractions (BTMR, HM, TTA) that we really want to see at night. It takes a lot of finagling in the current iteration to make this happen, sometime running multiple touring plans in one day to meet the desired goals. Thanks for acknowledging this and I look forward to using a “pin it” feature for upcoming visits. Thanks for what you do.
Len, I would really like this option. Right now I accomplish this by evaluating a plan or putting in a hard break. While we’re talking about enhancements, I’d love to see a way to indicate how important a “good seat” is to you for things like shows and especially parades. Plans don’t seem to add enough time to get curbside at at parades and as a short person I need to plan more time.
I would LOVE a pin feature. I do touring plans for clients and after getting certain aspects of their day optimized, I have to drag-n-drop the rest of the day and it takes forever. For example, maybe you have an appt at Bibbidi Bobbidi, so you want to stay around Fantasyland, so you would pin attractions around that time. Thanks Len!!
I would like to have the pin feature as well. We would like to do the Safari at AK first thing in the morning without a fastpass and at the end of our day again with a fastpass.
I just add a break at a nearby restaurant for both of them.
I have made many touring plans. I agree with other posts and will also add to the request for a “pin-it” feature. Thank you.
Adding to the chorus of I really want this option!!! Right now I try and figure out how long I will be in the line, and then I add in a break for that time. But it is super annoying.
OK. Let me see what we can do. Thanks Sarah!
I’m not seeing all the FREE plans. I only see a couple for each park, then it requires “Premium” access. Did I miss something?
Hey Jordan! You can make custom plans for any park for free. We’ll run it through the software and optimize it for you, too, and that’s free as well.
Also, Google Books has most recent Unofficial Guides scanned in and available for free online, including pages with the actual touring plans.
Great article, Len! When I am helping clients with their planning, I always buy them a subscription to the site. I’ve always loved using the optimizer for the “foundational” plan and then add my own constraints (e.g., try to hit Splash Mountain just before a mid-day break so they’re not walking around in wet clothes for 2 hours in the morning, or moving TTA to a later time to let them see Tomorrowland at night). It usually works out really well and gives people a more realistic idea of what they can do in a day. Keep up the great work!
Thanks Mush!
Question for ya’ll: In all your touring plans in the Unofficial Guide, you say for resort guests to get to the parks 30-50 mins before parks open, but non-resort guests to get there 50-70 minutes before parks open—why the difference in arrival times for resort and non-resort guests?
Thanks in advance for explaining 🙂
I’d be interested to know too
Ahh, got it.
The extra time for non-resort guests is for them to park in the parking lot, make it to the TTC, and then take the ferry or monorail over to the park entrance.
Resort guests get dropped off at the park entrance, so they don’t need the extra time for the ferry or monorail.
Let me know if that doesn’t make sense. We might be able to word this more clearly. Thanks!
Wow! Thanks for the great post. I loved the math and the tie-in to your unusual day at MK. I find computers very frustrating, but they are useful in many situations, including vacation planning. To say I am a Touring Plans fan is a vast understatement.
Thanks calcprof! I appreciate the support.