REVIEW 5 cited by
Human-aligned Chess with a Bit of Search
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Chess has long been a testbed for AI's quest to match human intelligence, and in recent years, chess AI systems have surpassed the strongest humans at the game. However, these systems are not human-aligned; they are unable to match the skill levels of all human partners or model human-like behaviors beyond piece movement. In this paper, we introduce Allie, a chess-playing AI designed to bridge the gap between artificial and human intelligence in this classic game. Allie is trained on log sequences of real chess games to model the behaviors of human chess players across the skill spectrum, including non-move behaviors such as pondering times and resignations In offline evaluations, we find that Allie exhibits humanlike behavior: it outperforms the existing state-of-the-art in human chess move prediction and "ponders" at critical positions. The model learns to reliably assign reward at each game state, which can be used at inference as a reward function in a novel time-adaptive Monte-Carlo tree search (MCTS) procedure, where the amount of search depends on how long humans would think in the same positions. Adaptive search enables remarkable skill calibration; in a large-scale online evaluation against players with ratings from 1000 to 2600 Elo, our adaptive search method leads to a skill gap of only 49 Elo on average, substantially outperforming search-free and standard MCTS baselines. Against grandmaster-level (2500 Elo) opponents, Allie with adaptive search exhibits the strength of a fellow grandmaster, all while learning exclusively from humans.
Forward citations
Cited by 5 Pith papers
-
Engine-Equal, Human-Unequal: A Reproducible Outcome Skew in Engine-Assessed Equal Chess Positions
Engine-equal chess positions carry small, reproducible human outcome skews that replicate across disjoint player groups, calendar halves, rating bands, and an out-of-sample month.
-
Understanding Reasoning from Pretraining to Post-Training
A joint scaling law: post-RL chess and math performance is predictable from pretraining loss, RL improvement rate grows with pretraining tokens, and RL both amplifies and discovers moves depending on difficulty.
-
Improving Human Performance with Value-Aware Interventions: A Case Study in Chess
Value-aware interventions using policy-value discrepancies outperform optimal-move recommendations from strong engines in improving human chess play.
-
Three-Body Alignment: Aligning Chess Agent with Human Reasoning through Reranked Rationale
Reranking retrieved grandmaster rationales by FEN similarity raises a chess LLM's semantic alignment with grandmaster explanations from 0.61 to 0.73 cosine similarity, while reducing tactical quality.
-
ChessMimic: Per-Rating Transformer Models for Human Move, Clock, and Outcome Prediction in Online Blitz Chess
Per-100-Elo-band transformers outperform Maia-2 in move prediction accuracy across all bands and reach 0.78 AUC on outcome prediction using held-out Lichess data.
Discussion (0). Sign in to comment.