LESSWRONG
LW

All of Sir Edmund's Comments + Replies

Red Pill vs Blue Pill, Bayes style
Sir Edmund40

"That means that for our posterior from above, if you choose blue, the probability of the majority choosing red is about 0.1817. If you choose red, it's the opposite: the probability that the majority will choose red is 1-0.1817 = 0.8183, over 4 times higher."

It may well be that I don't understand Beta priors, or maybe I just see myself as unique or non-representative. But intuitively, I would not think that my own choice can justify anywhere close to that large of a swing in my estimate of the probabilities of the majority outcome. Maybe I am subconsciously conflating this in my mind with the objective probability that I actually cast the tiebreaking vote, which is very small.

Reply
1ErickBall
I mean definitely most people will not use a decision procedure like this one, so a smaller update seems very reasonable. But I suspect this reasoning still has something in common with the source of the intuition a lot of people have for blue, that they don't want to contribute to anybody else dying.
D&D.Sci Dungeoncrawling: The Crown of Command Evaluation & Ruleset
Sir Edmund60

Thank you for making this. I have enjoyed following the D&D.Sci series, even though I don't get around to posting full solutions.

One thing that the series has given me is a better awareness of the limits of data science. Given enough time and effort, you can parse a data set along as many dimensions as you please, but the amount of time and effort needed grows exponentially based on the number of possible variables. If this scenario were a video game, I imagine that just controlling a party through a few different dungeons, and thereby seeing which ene... (read more)

Reply
6aphyer
+1. The fact that no-one's gotten the optimal solution is very much intended.  (If anyone had, I would be both very impressed with them and somewhat disappointed with myself.)  You should not expect to be able to fully model a domain with data science, it's like trying to thread a needle wearing huge thick gloves.  But you can expect to figure out something about the domain, and use that to at least substantially outperform randomness.  (Our highest scorer this round, abstractapplic, had ~half the optimal winrate, but ~100x the 'random approach' winrate).
D&D.Sci Dungeoncrawling: The Crown of Command
Sir Edmund30

Regarding the overall levels of successful teams: I was surprised to see that the total average level of adventurers on victorious teams was 3.69474, and on defeated teams it was 3.477. That's not as big a difference as might be guessed, and it suggests that the precise composition of the team (mix of types of adventurers) matters a lot more than the overall level. This is very helpful, because levels are the primary constraint on our resources.

To get possible insight into the various roles, I calculated the victory rates of teams that lacked a specific ty

... (read more)
Reply
D&D.Sci Dungeoncrawling: The Crown of Command
Sir Edmund30

If we filter the data based on the encounter which ended an unsuccessful Adventuring party, I notice that the groups foiled by Poison Needle Traps disproportionately had no Rogues.

Filtering by adventurer type, I notice that groups with no Rogues did not do well against dungeons with PNTs.

Thus, I think including at least one Rogue on the team heading for the Lost Temple of Lemarchand is wise.

Reply
3Sir Edmund