AlphaZero reveals new chess concepts learnable by top experts.
problem Extracting and understanding hidden knowledge from AI systems.
method Proposed method to extract new chess concepts from AlphaZero.
result Top chess grandmasters show improvements in learning new concepts.
Chess engines Stockfish and LCZero differ in their approach to solving endgame puzzles.
problem Comparing machine and human chess problem-solving abilities.
method Used Plaskett's Puzzle to compare Stockfish and LCZero's performance.
result Stockfish outperforms LCZero on the puzzle.
Transformers learn to predict chess moves with surprising accuracy and strength.
problem Training transformers on chess to predict moves accurately.
method Large-scale chess dataset (10M games), supervised learning with up to 270M parameters.
result Transformers can predict action-values for novel boards with high accuracy.
MuZero learns models to master complex games without domain knowledge.
problem Mastering complex, real-world domains with unknown dynamics.
method Combining tree-based search with learned models.
result Achieves superhuman performance in diverse domains.
The paper proposes a method to evaluate superhuman models by checking for logical inconsistencies.
problem Evaluating superhuman models when ground truth is hard to obtain.
method A framework using consistency checks to identify logical inconsistencies in model decisions.
result Logical inconsistencies can be discovered in superhuman model decisions across various tasks.
AlphaZero assesses new chess variants for balance and dynamics.
problem Designing engaging and balanced game rules, especially for chess variants.
method Used AlphaZero to learn near-optimal strategies for nine chess variants.
result AlphaZero reveals novel strategic and tactical patterns in chess variants.
We present an end-to-end learning method for chess, relying on deep neural networks. Without any a priori knowledge, in particular without any knowledge regarding the rules of chess, a deep neural network is trained using a combination of unsupervised pretraining and supervised training. The unsupervised training extra…
This article reports on an investigation of the use of convolutional neural networks to predict the visual attention of chess players. The visual attention model described in this article has been created to generate saliency maps that capture hierarchical and spatial features of chessboard, in order to predict the pro…
AlphaZero learns human chess knowledge during training.
problem Understanding how neural networks like AlphaZero acquire and represent human chess knowledge.
method Probed for a broad range of human chess concepts, analysed opening play, and investigated low-level representations.
result AlphaZero acquires and represents human chess knowledge during training.
This paper demonstrates the use of genetic algorithms for evolving: 1) a grandmaster-level evaluation function, and 2) a search mechanism for a chess program, the parameter values of which are initialized randomly. The evaluation function of the program is evolved by learning from databases of (human) grandmaster games…
In this paper we demonstrate how genetic algorithms can be used to reverse engineer an evaluation function's parameters for computer chess. Our results show that using an appropriate expert (or mentor), we can evolve a program that is on par with top tournament-playing chess programs, outperforming a two-time World Com…
Crazyhouse is a chess variant that incorporates all of the classical chess rules, but allows users to drop pieces captured from the opponent as a normal move. Until 2018, all competitive computer engines for this board game made use of an alpha-beta pruning algorithm with a hand-crafted evaluation function for each pos…
Dimensionality reduction is ubiquitous in analysis of complex dynamics. The conventional dimensionality reduction techniques, however, focus on reproducing the underlying configuration space, rather than the dynamics itself. The constructed low-dimensional space does not provide complete and accurate description of the…
In this paper we demonstrate how genetic algorithms can be used to reverse engineer an evaluation function's parameters for computer chess. Our results show that using an appropriate mentor, we can evolve a program that is on par with top tournament-playing chess programs, outperforming a two-time World Computer Chess …
FGNNs improve game-playing AI by exploiting symmetries.
problem Symmetrical game states are not exploited by current AI.
method Introduces FGNNs for creating group-equivariant neural networks.
result FGNNs improve performance in games like checkers and image segmentation.
This paper demonstrates the use of genetic algorithms for evolving a grandmaster-level evaluation function for a chess program. This is achieved by combining supervised and unsupervised learning. In the supervised learning phase the organisms are evolved to mimic the behavior of human grandmasters, and in the unsupervi…
Language models trained on chess board states outperform those on moves, even with causal masking.
problem Applying causal masking to spatial data for training unimodal language models.
method Trained bidirectional and causal self-attention models on both spatial (board-based) and sequential (move-based) chess data.
result Models trained on spatial board states achieve stronger playing strength than those trained on sequential data, even with causal masking.
We prove that the homotopy class of a Morin mapping f: P^p --> Q^q with p-q odd contains a cusp mapping. This affirmatively solves a strengthened version of the Chess conjecture [DS Chess, A note on the classes [S_1^k(f)], Proc. Symp. Pure Math., 40 (1983) 221-224] and [VI Arnol'd, VA Vasil'ev, VV Goryunov, OV Lyashenk…
In this paper we present the first results of a pilot experiment in the capture and interpretation of multimodal signals of human experts engaged in solving challenging chess problems. Our goal is to investigate the extent to which observations of eye-gaze, posture, emotion and other physiological signals can be used t…
From the early days of computing, games have been important testbeds for studying how well machines can do sophisticated decision making. In recent years, machine learning has made dramatic advances with artificial agents reaching superhuman performance in challenge domains like Go, Atari, and some variants of poker. A…
In this paper we construct and study a new 15-vertex triangulation X of the complex projective plane $\CP^2$. The automorphism group of X is isomorphic to S4×S3. We prove that the triangulation X is the minimal by the number of vertices triangulation of $\CP^2$ admitting a chess colouring of four-dimens…
Deep RL shows promise in algo trading, but more research needed.
problem Improving profitability in automated stock trading.
method Deep Reinforcement Learning applied to quantitative algo trading.
result Statistically significant improvements in performance, but no profitability.
Monte Carlo Tree Search improves financial derivative hedging efficiency.
problem Optimizing pricing and hedging of derivative contracts in incomplete markets.
method Integrates tree search techniques with Reinforcement Learning for optimal control problems.
result Monte Carlo Tree Search outperforms Q-learning in sample efficiency and learning speed. ESCHER avoids importance sampling to estimate regret in large games.
problem Estimating Nash equilibria in large games with high variance.
method Computes a history value function to estimate regret without importance sampling.
result ESCHER reduces regret estimation variance significantly compared to existing methods.
In ranking problems, the goal is to learn a ranking function from labeled pairs of input points. In this paper, we consider the related comparison problem, where the label indicates which element of the pair is better, or if there is no significant difference. We cast the learning problem as a margin maximization, and …
A core novelty of Alpha Zero is the interleaving of tree search and deep learning, which has proven very successful in board games like Chess, Shogi and Go. These games have a discrete action space. However, many real-world reinforcement learning domains have continuous action spaces, for example in robotic control, na…
AI stocks hedge against AI singularity's economic impact.
problem AI singularity's displacement of consumption.
method Developed an asset pricing model with incomplete markets.
result AI stocks command a premium due to market incompleteness.
Study analyzes AI's impact on firms, markets, and workers using large language model data.
problem Understanding AI's effect on firms, markets, and workers.
method Used 380 trillion tokens from 400+ large language models to analyze AI's impact.
result Firms with higher AI exposure earn higher returns, creating an AI premium.
New AI stock indices classify firms' AI engagement using 10-K filings.
problem Opaque AI selection criteria in existing ETFs.
method NLP analysis of 10-K filings to classify AI stocks.
result Companies with higher AI engagement have greater positive returns.
The paper analyzes risk spillovers between AI ETFs, AI tokens, and green markets.
problem Risk spillovers among AI ETFs, AI tokens, and green markets.
method R2 decomposition method
result AI ETFs and clean energy act as risk transmitters, while AI tokens and green assets act as receivers.
This review covers AI in finance, challenges, techniques, and opportunities.
problem Challenges and opportunities in AI applications in finance.
method Comprehensive categorization and overview of AI research in finance over decades.
result A dense roadmap of AI challenges, techniques, and opportunities in finance.
Explainable AI improves human decision accuracy but does not enhance it significantly.
problem Improving human decision-making through explainable AI.
method Comparing human decision accuracy with and without AI predictions, including or excluding explanations.
result Providing AI predictions improves human decision accuracy, but explanations do not significantly enhance it.
The paper explores AI in finance, focusing on XAI's role in enhancing interpretability and trust.
problem The need for AI in finance and the importance of XAI for better decision-making.
method Tracing AI's evolution in finance, highlighting XAI's role, and demonstrating through simulations.
result XAI enhances trust in AI systems, leading to more responsible decision-making.
Paper defines AI-specific loss reconstruction problem and introduces CER framework.
problem Reconstructing AI-generated losses, especially in agentic systems.
method CER framework: C (control boundary), E (evidence reconstruction), R (insurance response).
result Defines AI-specific reconstruction problem and operationalizes it.
Experiment shows cognitive biases impact human-AI collaboration, highlighting the need for diverse evaluator samples.
problem Cognitive biases affect human-AI collaboration, leading to suboptimal outcomes.
method Randomized experiment with 2,784 participants, manipulating AI suggestion quality, task burden, and financial incentives.
result Individual attitudes toward AI are the strongest predictor of performance, influencing accuracy and overcorrection.
AI enhances financial forecasting with challenges in regulation and privacy.
problem Challenges in integrating AI with financial services and regulations.
method Integration of AI technologies like deep learning and reinforcement learning.
result AI improves financial forecasting but faces regulatory and privacy issues.
AI+MPS workshop aims to strengthen AI's role in science.
problem AI's potential to enhance scientific discovery and education.
method Proposes activities and strategic priorities to strengthen AI-MPS link.
result AI and science are becoming increasingly intertwined.
Improved AI patent classifier measures U.S. and China's AI patenting.
problem Measuring AI patents with high precision and generalization.
method Fine-tuning PatentSBERTa on manually labeled data from USPTO's AI Patent Dataset.
result Rapid growth in AI patenting in both countries, but different organizational patterns.
FST.ai 2.0 improves Taekwondo decision-making with AI, reducing review time and increasing trust.
problem Fair, transparent, and explainable decision-making in Taekwondo.
method Pose-based action recognition, epistemic uncertainty modeling, interactive dashboards.
result 85% reduction in decision review time, 93% referee trust in AI-assisted decisions.
Article evaluates AI security threats and proposes multiple measures.
problem Threats to AI integrity and security.
method Literature review, analysis of AI supply chain, discussion of mitigations.
result Multiple protective measures are necessary for AI security.
Paper tackles AI risks by customizing metrics and models.
problem AI risks are multidimensional and immaturely managed.
method Decomposes AI risks into data protection, fairness, etc., and develops metrics and models.
result Customized metrics and models reduce AI risk uncertainty.
The DoD needs a robust process to evaluate AI/ML model performance and robustness.
problem AI/ML models are brittle and nonrobust, posing risks in national security.
method Reviews AI/ML development process and best practices for evaluation.
result Recommendations for DoD evaluators to ensure robust AI/ML capabilities.
Adversarial policies beat superhuman Go AI systems.
problem Vulnerability of superhuman AI systems to adversarial attacks.
method Training adversarial policies to trick KataGo into making blunders.
result Adversarial policies achieve >97% win rate against KataGo at superhuman settings.
AI threatens financial stability through misuse and stealth adoption.
problem Misuse and stealth adoption of AI in financial regulations.
method Analysis of AI's potential risks and criteria for AI suitability.
result AI will likely become widely used by stealth, affecting high-level financial functions.
Qlib aims to integrate AI into quantitative investment.
problem Challenges in applying AI to quantitative investment.
method Design and develop Qlib to accommodate AI-driven workflow.
result Qlib realizes the potential of AI technologies in quantitative investment.
Open AI models affect bond yields differently than closed ones.
problem Understanding how market reactions to AI releases impact bond yields.
method Analyzed US bond yields before and after the release of open and closed AI models.
result Open AI models shift bond yields in the opposite direction of closed models.
AI systems are being deployed to support human decision making in high-stakes domains. In many cases, the human and AI form a team, in which the human makes decisions after reviewing the AI's inferences. A successful partnership requires that the human develops insights into the performance of the AI system, including …
Do-AIQ framework evaluates AI algorithms' quality using DOE.
problem Quality evaluation of AI mislabel detection algorithms.
method Design-of-experiment approach with high-dimensional constraint space design and surrogate modeling.
result Established framework for evaluating AI algorithm quality robustly.