When will a single agent beat Minecraft (defeat the Ender dragon)?
21
254
2032
0.2%
Before 2023
13%
2023-2024
51%
2024-2025
22%
2025-2026
6%
2026-2027
4%
2027-2032
1.3%
2032-never
0.5%
Not by the end of 2027
I won't accept any algorithm that is substantially tuned for Minecraft specifically. If the same algorithm couldn't be adapted to other environments with similar results, it doesn't count.
Get Ṁ1,000 play money
Sort by:

Does this mean starring at the beginning of a new survival game on non-peaceful difficulty? Or does it include peaceful/creative mode/starting in the end with a bow?

@maskedtorah I'm not going to resolve to anything but the options I originally made.

@vluzko Apologies, I missed that the displayed list was truncated at first. Would delete if I could in the UI.

"Before 2023" seems very optimistic for an agent not tuned to Minecraft specifically, considering to my knowledge no agent tuned to Minecraft has done it yet. This sounds like it would require multi-domain training, which as of right now has comparable or worse results to specialization.

@horse I'm interpreting not tuned for minecraft as "could be used for another game if you trained it on it".
So my guess is that If someone makes something like a bigger VPT but trained on speedruning videos it would count.

@VictorLevoso Yes, that is what "not tuned for minecraft" means here: the agent itself can be tuned to minecraft, of course, but the learning algorithm generating it can't be