Wednesday, 21 January 2026

An Interesting Limit

Here is a report generated by Gemini Pro based on the content of this video. I found the video moved a little too quickly at times and the author read out every mathematical expression symbol by symbol which wasn't really necessary and it didn't aid comprehension. It's useful to be able to take the content of the video and put into a report that can be read at your leisure. If you want to tweak the LaTeX code, you can do so easily and I've done that below for a few of expressions.

The Limit of the nth Root: An Exploration of Euler's Sequence

At first glance, the limit of the sequence involving factorials and powers can seem intuitive, but as with many problems in analysis, the "obvious" answer can be misleading. This report dismantles the problem of finding the limit of the nth root of n factorial divided by n to the power of n. Following the path likely walked by Leonhard Euler, we move from discrete sequences to continuous calculus to find a beautiful truth connecting factorials, limits, and Euler’s number, e.

1. The Sequence and Intuition

We begin by defining our sequence \( a_n \):

$$ a_n = \frac{n!}{n^n} $$

Intuitively, the denominator \( n^n \) grows much faster than the numerator \( n! \), suggesting that the terms drop toward zero. To prove this rigorously, we employ the Ratio Test. We investigate the ratio of consecutive terms:

$$ \frac{a_{n+1}}{a_n} = \frac{(n+1)!}{(n+1)^{n+1}} \cdot \frac{n^n}{n!} $$

Simplifying the factorials (\( (n+1)! = (n+1)n! \)) and regrouping terms gives:

$$ \frac{a_{n+1}}{a_n} = \frac{(n+1) \cdot n^n}{(n+1)^{n+1}} = \frac{n^n}{(n+1)^n} = \left( \frac{n}{n+1} \right)^n $$

This expression can be rewritten to reveal a fundamental definition of Euler's number:

$$ \lim_{n \to \infty} \frac{a_{n+1}}{a_n} = \lim_{n \to \infty} \frac{1}{\left( \frac{n+1}{n} \right)^n} = \lim_{n \to \infty} \frac{1}{\left( 1 + \frac{1}{n} \right)^n} = \frac{1}{e} $$

Since \( \dfrac{1}{e} \approx 0.3679 \) is strictly less than 1, the Ratio Test confirms that the sequence converges to 0.

2. The Main Problem: The nth Root

Establishing that the base sequence goes to 0 is just the preamble. The true challenge is finding the limit of the nth root of this sequence:

$$ L = \lim_{n \to \infty} \sqrt[n]{a_n} = \lim_{n \to \infty} \left( \frac{n!}{n^n} \right)^{\frac{1}{n}} $$

Since the base approaches 0 and the exponent \( \frac{1}{n} \) also approaches 0, we are facing the indeterminate form \( 0^0 \). To resolve this, we use the natural logarithm to transform the product into a sum, bridging the gap between discrete algebra and integral calculus.

3. From Logarithms to Riemann Sums

Let \( y = \sqrt[ \uproot{4} n]{a_n} \). Taking the natural log of the limit allows us to work with sums:

$$ \ln(L) = \lim_{n \to \infty} \ln \left( \left( \frac{n!}{n^n} \right)^{\frac{1}{n}} \right) = \lim_{n \to \infty} \frac{1}{n} \ln \left( \frac{n!}{n^n} \right) $$

Using logarithm rules, we expand the term inside:

$$ \ln \left( \frac{n!}{n^n} \right) = \ln(n!) - \ln(n^n) = \sum_{k=1}^{n} \ln(k) - n \ln(n) $$

We can cleverly rewrite \( n \ln(n) \) as a sum of \( n \) identical terms: \( \displaystyle \sum_{k=1}^{n} \ln(n) \). Substituting this back into our limit equation gives:

$$ \ln(L) = \lim_{n \to \infty} \frac{1}{n} \left( \sum_{k=1}^{n} \ln(k) - \sum_{k=1}^{n} \ln(n) \right) = \lim_{n \to \infty} \frac{1}{n} \sum_{k=1}^{n} \left( \ln(k) - \ln(n) \right) $$

Combining the logs, we arrive at a recognizable form:

$$ \ln(L) = \lim_{n \to \infty} \frac{1}{n} \sum_{k=1}^{n} \ln \left( \frac{k}{n} \right) $$

This structure—a sum of function values multiplied by a small width \( \frac{1}{n} \) is precisely the definition of a Riemann Sum on the interval \([0, 1]\). As \( n \to \infty \), the sum converges to a definite integral:


$$ \ln(L) = \int_{0}^{1} \ln(x) \, dx $$

4. Evaluating the Integral

We now evaluate the improper integral of \( \ln(x) \) from 0 to 1. Using integration by parts (where \( u = \ln(x) \) and \( dv = dx \)), we get:

$$ \int \ln(x) \, dx = x \ln(x) - x $$

We evaluate the definite integral by taking the limit as the lower bound approaches 0:

$$ \Bigl[ x \ln(x) - x \Bigr]_0^1 = (1 \ln(1) - 1) - \lim_{a \to 0^+} (a \ln(a) - a) $$

We know \( \ln(1) = 0 \), so the first term is \( -1 \). For the limit \( \lim_{a \to 0^+} a \ln(a) \), we use L'Hôpital's rule, which shows that this term vanishes to 0. Thus:

$$ \ln(L) = -1 - 0 = -1 $$

Conclusion

We have found that the natural logarithm of the limit is \( -1 \). To find the original limit \( L \), we simply exponentiate both sides:

$$ L = \lim_{n \to \infty} \left( \frac{n!}{n^n} \right)^{\frac{1}{n}}=e^{-1} = \frac{1}{e} $$

We have proven that while the sequence \( \dfrac{n!}{n^n} \) collapses to zero, its geometric mean—the nth root—stabilizes at exactly 1 over e. This problem serves as an elegant bridge connecting basic sequence properties, the definition of e, and the power of integral calculus.

Tuesday, 20 January 2026

Newton's Approximation For Pi

I watched an interesting YouTube video about how Newton approximated \( \pi \) and I thought it would be an interesting exercise to get Gemini to access the video and recreate the steps outlined. Once Gemini had created its response, I then got it to create a HTML version of the information for easy pasting into Blogger. Here is what it came up with and it's really quite impressive:

Based on the video provided, specifically the section starting around [00:06:50], here is the step-by-step derivation of Newton’s approximation of $\pi$.

Newton's method combines two different ways of calculating the area of a specific portion of a circle: using calculus (integration of an infinite series) and geometry. By equating these two results, he solved for $\pi$.

Step 1: The Equation of the Circle

Newton started with the equation of a unit circle centered at the origin:

$$x^2 + y^2 = 1$$

Solving for $y$ gives the function for the upper semicircle:

$$y = \sqrt{1 - x^2} = (1 - x^2)^{\frac{1}{2}}$$

Newton wanted to find the area under this curve from $x = 0$ to $x = \frac{1}{2}$. This can be expressed as the definite integral:

$$\text{Area} = \int_{0}^{\frac{1}{2}} (1 - x^2)^{\frac{1}{2}} \, dx$$

Step 2: Binomial Expansion

Since calculus was in its infancy, Newton applied his generalized binomial theorem to expand $(1 - x^2)^{\frac{1}{2}}$ into an infinite series. The general form for $(1+u)^n$ is:

$$(1+u)^n = 1 + nu + \frac{n(n-1)}{2!}u^2 + \frac{n(n-1)(n-2)}{3!}u^3 + \dots$$

By substituting $u = -x^2$ and $n = \frac{1}{2}$, he derived the series for the circle's equation:

$$(1 - x^2)^{\frac{1}{2}} = 1 - \frac{1}{2}x^2 - \frac{1}{8}x^4 - \frac{1}{16}x^6 - \frac{5}{128}x^8 - \dots$$

Step 3: Term-by-Term Integration

Newton then found the area (fluxion) by integrating the series term by term:

$$\int \left( 1 - \frac{1}{2}x^2 - \frac{1}{8}x^4 - \frac{1}{16}x^6 - \dots \right) \, dx$$

This yields the algebraic formula for the area:

$$\text{Area}(x) = x - \frac{1}{6}x^3 - \frac{1}{40}x^5 - \frac{1}{112}x^7 - \frac{5}{1152}x^9 - \dots$$

Step 4: Calculating the Area for $x = \frac{1}{2}$

Newton improved efficiency by choosing the limit $x = \frac{1}{2}$ (instead of 1), which makes the powers of $x$ shrink very rapidly. Substituting $x = \frac{1}{2}$ into the series:

$$\text{Area} \approx \frac{1}{2} - \frac{1}{6}\left(\frac{1}{2}\right)^3 - \frac{1}{40}\left(\frac{1}{2}\right)^5 - \frac{1}{112}\left(\frac{1}{2}\right)^7 - \dots$$

Simplifying the fractions:

$$\text{Area} \approx \frac{1}{2} - \frac{1}{48} - \frac{1}{1280} - \frac{1}{14336} - \dots$$

This sum gives a numerical value for the area.

Step 5: Equating to Geometry



Screenshot from video

Geometrically, the area under the unit circle from $x=0$ to $x=\frac{1}{2}$ corresponds to a slice of the circle. As described in the video, this region consists of two shapes:

  1. A triangle with base $\frac{1}{2}$ and height $\frac{\sqrt{3}}{2}$ (since $y = \sqrt{1 - (0.5)^2} = \sqrt{0.75} = \frac{\sqrt{3}}{2}$).
  2. A circular sector of $30^{\circ}$ (or $\frac{\pi}{6}$ radians).

The total geometric area is:

$$\text{Area} = \text{Area}_{\text{triangle}} + \text{Area}_{\text{sector}}$$ $$\text{Area} = \left( \frac{1}{2} \cdot \text{base} \cdot \text{height} \right) + \left( \frac{\theta}{2\pi} \cdot \pi r^2 \right)$$ $$\text{Area} = \left( \frac{1}{2} \cdot \frac{1}{2} \cdot \frac{\sqrt{3}}{2} \right) + \left( \frac{\pi/6}{2\pi} \cdot \pi (1)^2 \right)$$ $$\text{Area} = \frac{\sqrt{3}}{8} + \frac{\pi}{12}$$

Step 6: Solving for $\pi$

Finally, Newton equated the Algebraic Area (from Step 4) with the Geometric Area (from Step 5) and solved for $\pi$:

$$\frac{\sqrt{3}}{8} + \frac{\pi}{12} = \text{Series Sum}$$ $$\frac{\pi}{12} = \text{Series Sum} - \frac{\sqrt{3}}{8}$$ $$\pi = 12 \left( \text{Series Sum} - \frac{\sqrt{3}}{8} \right)$$ $$\pi = 12 \left[ \left( \frac{1}{2} - \frac{1}{48} - \frac{1}{1280} - \dots \right) - \frac{\sqrt{3}}{8} \right]$$

Using just the first few terms of the series, Newton achieved an approximation of $\pi \approx 3.14161$.

Friday, 16 January 2026

Fibonacci-Related Numbers

My diurnal age today is \( \textbf{28047} \) and this number has the interesting property that it's part of a Fibonacci sequence with seed numbers of 3 and 9. This leads to the following sequence of numbers:

3, 9, 12, 21, 33, 54, 87, 141, 228, 369, 597, 966, 1563, 2529, 4092, 6621, 10713, 17334, 28047, ...

These initial numbers form part of OEIS A022379

The thought occurred to me that given two seed digits between 0 and 9, there ought to be a limited set of numbers from 10 to let's say 40000 that are generated by two single digit seeds. I got Gemini to write a Python program (permalink) to investigate this and it turns out that there are 651 numbers with this property. Here they are:

10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 107, 108, 109, 110, 111, 112, 113, 115, 116, 117, 118, 120, 121, 123, 124, 125, 126, 128, 129, 131, 133, 134, 136, 137, 138, 139, 141, 142, 144, 146, 147, 149, 150, 152, 154, 155, 157, 159, 160, 162, 163, 165, 167, 168, 170, 173, 175, 176, 178, 180, 181, 183, 186, 188, 189, 191, 194, 196, 199, 201, 202, 204, 207, 209, 212, 215, 217, 220, 222, 223, 225, 228, 230, 233, 236, 238, 241, 243, 246, 249, 251, 254, 257, 259, 262, 264, 267, 270, 272, 275, 280, 283, 285, 288, 291, 293, 296, 301, 304, 306, 309, 314, 317, 322, 325, 327, 330, 335, 338, 343, 348, 351, 356, 359, 361, 364, 369, 372, 377, 382, 385, 390, 393, 398, 403, 406, 411, 416, 419, 424, 427, 432, 437, 440, 445, 453, 458, 461, 466, 471, 474, 479, 487, 492, 495, 500, 508, 513, 521, 526, 529, 534, 542, 547, 555, 563, 568, 576, 581, 584, 589, 597, 602, 610, 618, 623, 631, 636, 644, 652, 657, 665, 673, 678, 686, 691, 699, 707, 712, 720, 733, 741, 746, 754, 762, 767, 775, 788, 796, 801, 809, 822, 830, 843, 851, 856, 864, 877, 885, 898, 911, 919, 932, 940, 945, 953, 966, 974, 987, 1000, 1008, 1021, 1029, 1042, 1055, 1063, 1076, 1089, 1097, 1110, 1118, 1131, 1144, 1152, 1165, 1186, 1199, 1207, 1220, 1233, 1241, 1254, 1275, 1288, 1296, 1309, 1330, 1343, 1364, 1377, 1385, 1398, 1419, 1432, 1453, 1474, 1487, 1508, 1521, 1529, 1542, 1563, 1576, 1597, 1618, 1631, 1652, 1665, 1686, 1707, 1720, 1741, 1762, 1775, 1796, 1809, 1830, 1851, 1864, 1885, 1919, 1940, 1953, 1974, 1995, 2008, 2029, 2063, 2084, 2097, 2118, 2152, 2173, 2207, 2228, 2241, 2262, 2296, 2317, 2351, 2385, 2406, 2440, 2461, 2474, 2495, 2529, 2550, 2584, 2618, 2639, 2673, 2694, 2728, 2762, 2783, 2817, 2851, 2872, 2906, 2927, 2961, 2995, 3016, 3050, 3105, 3139, 3160, 3194, 3228, 3249, 3283, 3338, 3372, 3393, 3427, 3482, 3516, 3571, 3605, 3626, 3660, 3715, 3749, 3804, 3859, 3893, 3948, 3982, 4003, 4037, 4092, 4126, 4181, 4236, 4270, 4325, 4359, 4414, 4469, 4503, 4558, 4613, 4647, 4702, 4736, 4791, 4846, 4880, 4935, 5024, 5079, 5113, 5168, 5223, 5257, 5312, 5401, 5456, 5490, 5545, 5634, 5689, 5778, 5833, 5867, 5922, 6011, 6066, 6155, 6244, 6299, 6388, 6443, 6477, 6532, 6621, 6676, 6765, 6854, 6909, 6998, 7053, 7142, 7231, 7286, 7375, 7464, 7519, 7608, 7663, 7752, 7841, 7896, 7985, 8129, 8218, 8273, 8362, 8451, 8506, 8595, 8739, 8828, 8883, 8972, 9116, 9205, 9349, 9438, 9493, 9582, 9726, 9815, 9959, 10103, 10192, 10336, 10425, 10480, 10569, 10713, 10802, 10946, 11090, 11179, 11323, 11412, 11556, 11700, 11789, 11933, 12077, 12166, 12310, 12399, 12543, 12687, 12776, 12920, 13153, 13297, 13386, 13530, 13674, 13763, 13907, 14140, 14284, 14373, 14517, 14750, 14894, 15127, 15271, 15360, 15504, 15737, 15881, 16114, 16347, 16491, 16724, 16868, 16957, 17101, 17334, 17478, 17711, 17944, 18088, 18321, 18465, 18698, 18931, 19075, 19308, 19541, 19685, 19918, 20062, 20295, 20528, 20672, 20905, 21282, 21515, 21659, 21892, 22125, 22269, 22502, 22879, 23112, 23256, 23489, 23866, 24099, 24476, 24709, 24853, 25086, 25463, 25696, 26073, 26450, 26683, 27060, 27293, 27437, 27670, 28047, 28280, 28657, 29034, 29267, 29644, 29877, 30254, 30631, 30864, 31241, 31618, 31851, 32228, 32461, 32838, 33215, 33448, 33825, 34435, 34812, 35045, 35422, 35799, 36032, 36409, 37019, 37396, 37629, 38006, 38616, 38993, 39603, 39980

The following code (permalink) can be used to find the seeds of any number in this list. It's not impressive code I'm sure but it seems to do the job. Let's try with the last number in the previous list, 39980.

c=39980 L=[] b=round(c/((1+sqrt(5))/2)) L.append(c);L.append(b) a=0 while b>=a and c>b: a=c-b if a <b: c=b b=a L.append(a) L.reverse() if len(str(L[1]))==2: a=L[1]-L[0] b=L[0] print("Seed numbers for Fibonacci sequence are", a,"and",b) X=[a,b] L.remove(L[0]) print(X+L) else: print("Seed numbers for Fibonacci sequence are", L[0],"and",L[1]) print(L)


Seed numbers for Fibonacci sequence are 9 and 4

[9, 4, 13, 17, 30, 47, 77, 124, 201, 325, 526, 851, 1377, 2228, 3605, 5833, 9438, 15271, 24709, 39980]


Interestingly, 39980 is listed in the OEIS as OEIS A022132 but the seeds are listed as 4 and 13 but this is equivalent of course to seeds of 9 and 4. Zero can be a seed number in the first position but it can't then be followed by another zero and so there are 10 x 9 = 90 distinct pairs of single digit seeds. 

Two different pairs of single digit seeds can lead to the same sequence. For example:
  • seeds of 1 and 3 \( \rightarrow\) 1, 3, 4, 7, 11, 18, 29, ...
  • seeds of 2 and 1 \( \rightarrow \) 2, 1, 3, 4, 7, 11, 18, 29, ...
Figure 1 shows a plot of these Fibonacci-related numbers and it's interesting that they form a definite exponential curve with the density of points noticeably thinning out as the numbers become larger.


Figure 1
ADDENDUM:

After completing this post, I discovered that I'd already covered this topic in a post from Thursday, 12th June 2025 titled Fibonacci Numbers Derived From Single Digits. However, in that post I only considered seed digits where the first was smaller than the second and so I discounted a number like 59 because it requires seed digits of 7 and 3 such that the sequence 7, 3, 10, 13, 23, 36, 59 is generated.

Thursday, 15 January 2026

What's Special About 28046?


Figure 1

Figure 1 shows a screenshot of a post that I uploaded on the 27th September 2022 in which I noted that the number 26840 contained all the even digits exactly once. Today I turned 28046 days old and this number is the next such number after 26840 with this property. There are only 96 such numbers overall and as I also noted in my blog post at the time:

"I'll only see another six such numbers in my lifetime: 28046, 28064, 28406, 28460, 28604, 28640."

THE 28046 MONUMENT: A COLOSSAL ACHIEVEMENT

So, one down and five to go with the next one only 18 days away. After that, there's a gap of more than a year. The property of these numbers is very much base dependent of course but nonetheless interesting from a recreational mathematical perspective.

Monday, 12 January 2026

Bogey Numbers


Video based on blog content, generated by NotebookLM

In a darts match, once you reach a score of between 170 and 2 inclusive, you can defeat your opponent with one, two or three darts provided you score doesn't correspond to one of the so-called "bogey numbers". These numbers are:

  • \(169 =13^2 \)
  • \(168=2^3 \times 3 \times 7 \)
  • \(166=2 \times 83 \)
  • \(165=3 \times 5 \times 11\)
  • \(163 \text{ is prime} \)
  • \(162 = 2 \times 3^4\)
  • \(159 = 3 \times 53\)
The maximum of score of 170 can be finished with two consecutive treble 20s followed by 50 (the red of the bullseye equivalent to 2 x 25). With a score of 2, you finish the match off with a single dart directed at double 1.

With my 77th birthday fast approaching, I wanted to consider how many ways there are to finish off a darts match from a score of 77. It turns out that there are 905 different ways (permalink) using two or three darts. Here are the possible two dart finishes:

  • 2-Darts: T9, DBull
  • 2-Darts: T13, D19
  • 2-Darts: T15, D16
  • 2-Darts: T17, D13
  • 2-Darts: T19, D10
The other 900 ways involve three darts, for example:  S1, D13, DBull. Figure 1 shows a plot of the total numbers of ways to finish for scores between 2 and 170. Click to enlarge. A score of 58 offers the largest number of ways to check out, 1404.


Figure 1: permalink

Of course professional darts players only choose from a very narrow selection out of all these possibilities as Gemini explains.

You have hit on the fundamental difference between the math of darts (which is what the code calculates) and the art of darts (which is what pros play).

While Python might find 50 ways to check out a score, a professional like Michael van Gerwen or Luke Littler might only ever consider one or two of them.


Infographic based on blog content
generated by NotebookLM


Here is the breakdown of the logic top players use to filter those thousands of possibilities down to the "correct" shot.

1. The Principle of "Splitting the Double" (The Safety Net)

This is the single most important rule in professional darts. Pros prioritize doubles that can be halved (split) and still remain a double if they miss into the single segment.

  • The "King" Double is D16 (32):

    • If you aim for D16 (32) and hit Single 16, you have 16 left. That is D8.

    • If you aim for D8 and miss into S8, you have 4 left (D2).

    • If you aim for D2 and miss into S2, you have 2 left (D1).

    • Result: You have 4 layers of safety. You can miss your double 3 times and still be on a finish without needing a "setup" dart to get back to an even number.

  • The Problem with D20 (Tops):

    • D20 is popular, but less safe. If you miss D20 (40) and hit S20, you have 20 left (D10).

    • If you miss D10 (20) and hit S10, you have 10 left (D5).

    • D5 is an odd number. You cannot finish on 5. You must now waste a dart hitting a Single 1 to leave D2.

The Decision: If a pro has a choice between leaving D20 or D16, they will almost always maneuver to leave D16.

2. "Percentage Darts" (Managing the Miss)

Pros assume they might miss the Triple and hit a Single. They choose routes where a "bad" throw (a single) still leaves a finishable score.

  • Example: You have 61 points left with 2 darts.

    • The "Amateur" Math Route: Triple 15 (45) leaves D8 (16).

      • Risk: If you miss T15 and hit S15, you have 46 left. You have 1 dart remaining. You cannot check out 46 with 1 dart. Turn over.

    • The "Pro" Route: Single 25 (Outer Bull) leaves D18 (36).

      • Safety: If you miss the Bull and hit S25, you have 36 left (D18). If you miss widely and hit S11 (a common neighbor to the bull), you have 50 left (Double Bull). You still have a shot at a double.

The Decision: The pro chooses the route where a miss keeps the turn alive.

3. Avoiding the "Bogey" Singles (Odd vs. Even)

The goal is to get to an even number as fast as possible.

  • If you are on an odd number (e.g., 17, 33, 45), you must hit an odd segment to get to an even finish.

  • If you are on an even number, you must hit an even segment (or a Triple even) to stay even.

Pros hate finishing on odd doubles (D19, D17, D15, etc.) because if they hit the single, they are stuck on an odd number again.

  • Bad: Aiming for D19 (38). Hit S19. Left with 19. Now you need S3 to leave D8. It's messy.

  • Good: Aiming for D18 (36). Hit S18. Left with 18 (D9). Still messy, but D18 is physically close to D4 and D1, making the recovery easier.

4. Board Management (Staying in Rhythm)

Dart players rely heavily on muscle memory. They prefer routes that require minimal movement around the board.

  • Example: 82 left.

    • Option A: Bull (50) + D16 (32). (Requires moving from center to right edge).

    • Option B (Pro Preference): D20 (40) + S10 + D16? No.

    • Option C (The "Top" Route): T14 (42) leaves D20 (40).

    • The "Phil Taylor" Route: Bull (50) leaves D16. (Some pros love the Bull because it fixes "messy" math instantly).

5. The "Matchplay" Factor (Aggressive vs. Conservative)

Finally, the choice depends on what the opponent is doing.

  • Scenario A: Opponent is way back (on 300 points).

    • Strategy: Go safe. Don't try a risky T20-T20-D20 finish. Just hit big scores to get down to D16 reliably. Use 3 darts to set up the perfect number.

  • Scenario B: Opponent is on a finish (e.g., 32).

    • Strategy: Aggressive. You must check out this turn. If you have 170, you must go T20-T20-Bull. You don't care about safety; you care about possibility.

Summary: The "Pro" Algorithm

If you were to program a "Pro Bot" rather than a "Math Bot," the logic would look like this:

  1. Can I finish this turn?

  2. If yes: Pick the route where a single (missed triple) leaves a finish for the next dart.

  3. If no: Pick the route that leaves 32 (D16) or 40 (D20) for the next turn.

  4. Avoid: Any route that leaves an odd number remainder.

Gemini created a program that will calculate the better choices when considering checking out. Figure 2 shows what it suggests for 77 (permalink).


Figure 2