Projects

Exact agent evaluation and failure analysis for self-play Q-learning

Question
Can apparently competent self-play Q-policies still be systematically exploitable?
Result
Exact best-response evaluation found force-loss exploits in 6/6 baseline checkpoint-seat policies. Controlled changes reduced this to 0/6.
Contribution
A reproducible failure-analysis study separating sampled opponent robustness, adversarial Bellman objectives, and symmetry-aware evidence pooling.
Evidence
Public repository · frozen checkpoints · exact best-response evaluator · controlled experiment reports · 24-test suite · machine-readable metrics

Research question

Sampled matches can make a self-play agent look competent while leaving a systematic counter-policy undiscovered. This study asks which failures become visible when every frozen policy is evaluated against an exact best response, and which controlled interventions remove them under matched Q-update budgets.

Tic-Tac-Toe is used as an exhaustively searchable testbed, not as the product. The focus is agent evaluation, causal failure analysis, and reproducible experimental reasoning.

Controlled experiment chain

Method Force-loss exploitable policies Strategic tests
Sampled self-play 6/6 16/21
+ Opponent mixture 6/6 20/21
+ Adversarial backup 4/6 20/21
+ Adversarial backup + D4 0/6 21/21

The controlled progression from sampled self-play to adversarial backup plus D4 symmetry

Opponent mixture improved sampled behavior and repaired a visible local error, but exact evaluation still found all six policies exploitable. Changing the Bellman backup to minimize over legal opponent responses reduced exploitability to 4/6 and changed the residual failure from confident misvaluation to sparse updates and unresolved ties. D4 canonicalization then pooled equivalent evidence across rotations and reflections without increasing the update budget.

Mechanism evidence

D4 canonicalization compressed the reachable representation

Evidence pooling corrected the action ranking in a historically sparse state

Reproducibility and limits

The repository includes fixed seeds, twelve frozen checkpoints, machine-readable metrics, exact exploit trajectories, experiment reports, and tests covering perspective semantics, terminal backups, legal actions, exact best response, and D4 mappings. The technical research note explains the causal chain and evidence boundary.

Public artifacts