MétaCan
Menu
Back to cohort

On-Policy Vs. Off-Policy Reinforcement Learning in ConnectX: Seat-Stratified Performance and the Role of Action Masking

2025· article· W4416125924 on OpenAlexaff

Bibliographic record

VenueApplied and Computational Engineering · 2025
Typearticle
Language
FieldComputer Science
TopicReinforcement Learning in Robotics
Canadian institutionsMcGill University
Fundersnot available
KeywordsPoolingRobustness (evolution)GeneralizationMasking (illustration)Reinforcement learningReinforcementLeverSet (abstract data type)

Abstract

fetched live from OpenAlex

This study evaluates on-policy and off-policy reinforcement learning for ConnectX under a unified, seat-stratified evaluation protocol, with particular attention to invalid-action masking. Policies are trained against a fixed opponent schedule and evaluated offline with frozen parameters. The test set distinguishes Seen opponents from Unseen, deeper search (noisy-minimax-3 as the primary adversary; clean minimax-3 as a stress test). Uncertainty is summarized with 95% Wilson intervals, and all outcomes are reported by seat to avoid pooling bias. Across Seen opponents, masking consistently accelerates policy-gradient learning and reduces variability: MaskablePPO reaches target win-rate levels with fewer samples and tighter intervals than PPO, while value-based baselines reach an early asymptote. Against the Unseen noisy-minimax-3 in the first seat, PPO exceeds MaskablePPO (71.9% vs. 37.5%; intervals non-overlapping), whereas in the second seat masking yields large margins where legal actions are scarce (e.g., 87.6% vs. 17.3% against noisy-minimax-2; 48.3% vs. 8.3% against blocker; intervals non-overlapping). Against clean minimax-3, win rates approach zero within CI in the second seat for all methods, indicating a persistent gap to deeper search. These results imply two practical guidelines for legality-constrained, turn-based games: (i) legality-aware sampling is a substantive stability lever for policy-gradient methods rather than a peripheral implementation detail; and (ii) seat-stratified reporting is required to disentangle structural initiative from algorithmic effects. Overall, masking improves in-distribution efficiency and second-seat robustness but does not by itself close the generalization gap to stronger, unseen search.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.882
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.006
GPT teacher head0.224
Teacher spread0.218 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueApplied and Computational EngineeringSame topicReinforcement Learning in RoboticsFrench-language works237,207