Playing Various Strategies in Dominion with Deep Reinforcement Learning
Bibliographic record
Abstract
Deck-building games, like Dominion, present an unsolved challenge for game AI research. The complexity arising from card interactions and the relative strength of strategies depending on the game configuration result in computer agents being limited to simple strategies. This paper describes the first application of recent advances in Geometric Deep Learning to deck-building games. We utilize a comprehensive multiset-based game representation and train the policy using a Soft Actor-Critic algorithm adapted to support variable-size sets of actions. The proposed model is the first successful learning-based agent that makes all decisions without relying on heuristics and supports a broader set of game configurations. It exceeds the performance of all previous learning-based approaches and is only outperformed by search-based approaches in certain game configurations. In addition, the paper presents modifications that induce agents to exhibit novel human-like play strategies. Finally, we show that learning strong strategies based on card combinations requires a reinforcement learning algorithm capable of discovering and executing a precise strategy while ignoring simpler suboptimal policies with higher immediate rewards.
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 imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
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".