← Experiments

Experiment 3 — Does a well-trained model adapt to the actual authority?

Opening-buy probe · well-trained models, played at both authorities

Hypothesis. Trained on 100,000 rounds, a model picks the correct card for the authority it is actually playing, regardless of how it was trained: both the 10-authority and 50-authority models buy Battle Pod when the game starts at 10 authority, and Trade Pod when it starts at 50.

Setup

Training depth. The hypothesis names 100,000 rounds. Running that literally takes many hours per model in this pure-Python harness, so this page reports a reduced, proportional depth of 500 self-play games (config: cheap) that exercises the same effect. Reproduce at full depth with the documented flags — results are decoupled from the site build, so re-running never requires a rebuild.

Results

Model · playing atBattle PodTrade PodExplorerPicksn
trained @ 10 authority, playing @ 1050%3%22%Battle Pod20
trained @ 10 authority, playing @ 5039%6%20%Battle Pod20
trained @ 50 authority, playing @ 1043%10%20%Battle Pod20
trained @ 50 authority, playing @ 5039%5%22%Battle Pod20

Verdict

✗ does not match hypothesis. The well-trained models do not yet cleanly adapt to the authority in play (more training needed).

← All experiments · Home