feat(training): add opt-in teamplay evaluation

This commit is contained in:
Josh Creek
2026-09-01 17:30:40 +01:00
parent 9004800326
commit 7b2f9c26f4
8 changed files with 84 additions and 11 deletions
+6 -1
View File
@@ -667,7 +667,12 @@ can be based on evidence instead of a single watched match.
Stage 7 teamplay remains deliberately unconfigured. The fixed roster
observation and `team_size` plumbing can run 2v2, but there is no paired 2v2
evaluation or team-credit reward yet; spending 120M steps without those gates
would make a pass meaningless.
would make a pass meaningless. The prerequisites are now implemented but
remain opt-in: `ShipAIController.team_touch_credit_weight` shares a bounded
fraction of a touch payout across same-team agents (default `0.0` preserves
all existing curricula), and `evaluate.py --team-size=2` runs the same policy
as a two-ship team with the existing paired side swap. Stage 7 stays
unconfigured until a recorded 2v2 evaluation establishes teamplay gates.
`training/generation5.py` implements Stages 46 separately from the completed
generation-4 orchestrator and state. It always begins Stage 4 from