TReC: Evaluating Move-Induced State Changes in Instruction-Conditioned Go
Organizations: University of California, San Diego · University of Melbourne · University of Virginia · Shanghai Jiao Tong University ·
Abstract
When a Go model predicts a move different from the expert's, coordinate distance measures how far the prediction lands from the reference. We introduce Transition Representation Consistency (TReC) to compare how the two moves change a board-state embedding. Both moves are executed from the same position under the game rules, and TReC is the cosine similarity between the two resulting representation changes. In experiments with a frozen KataGo network on 680 mid-to-late-game positions from five games, the gap between the highest and lowest candidate per position has a median of 0.01 to 0.08 for the direct successor-state cosine and 0.88 to 1.33 for TReC, depending on the evaluator layer. TReC follows coordinate distance only weakly: the rank correlation between a candidate's distance to the reference and its TReC, computed within each position, has a median of -0.19 over these positions.
Figures & tables
| TReC | Successor cosine | |||||
|---|---|---|---|---|---|---|
| Candidate | bias2 | act2 | conv2p | bias2 | act2 | conv2p |
| below | ||||||
| right | ||||||
| Minimum | ||||||
| Median | ||||||
Appendix figures & tables1 asset
Supplementary material from the paper’s appendix.
Appendix
State Representation Learning
State representation learning develops compact, task-relevant descriptions of observations and histories for prediction, control, and decision-making.
See all 132 papers