Genetic algorithms improve computer chess programs to grandmaster level.
problem Improving computer chess programs to match human grandmaster performance.
method Evolved a grandmaster-level evaluation function and search mechanism using genetic algorithms.
result The evolved program outperforms a world champion and matches other top programs.
Expert-driven genetic algorithms improve chess evaluation functions.
problem Creating efficient evaluation functions for complex systems.
method Using genetic algorithms with expert guidance to evolve evaluation functions.
result Evolved programs outperform top chess programs with fewer parameters.
Genetic algorithms optimize chess evaluation functions with mentor assistance.
problem Optimizing complex evaluation functions for superior performance.
method Genetic algorithms with mentor-assisted evolution.
result Programs evolved with mentors outperform top chess champions.
Paper evolves a grandmaster-level chess evaluation function.
problem Creating a chess program that can play at grandmaster level.
method Combining supervised and unsupervised learning with genetic algorithms.
result The evolved program outperforms a two-time World Computer Chess Champion.
Deep learning predicts chess player attention using eye-tracking and game data.
problem Predicting chess player attention during game.
method Convolutional neural networks with skip-layer architecture and autoencoder.
result Deep features from natural images help in predicting saliency maps for chess.
Engine SixtyFour uses neural networks to play Crazyhouse chess.
problem Developing a neural network-based evaluation function for Crazyhouse chess.
method Created an ensemble model for Crazyhouse chess using a neural network.
result Early versions of the network have a playing level comparable to a strong amateur.
DeepChess learns chess without rules, matching top programs.
problem Teaching AI to play chess without human intervention.
method End-to-end deep neural network trained on millions of games.
result DeepChess performs at grandmaster level.
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.
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.
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.
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.
Pilot study shows multimodal signals improve chess expertise detection.
problem Detecting chess expertise through multimodal signals.
method Multimodal observation of chess players' eye-gaze, posture, emotion, and body language.
result Multimodal approach reaches up to 93% accuracy in detecting chess expertise compared to 86% with unimodal approach.
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.
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…
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.
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…
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.
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 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…
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. 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 …
AR CI framework handles complex confounders and sequential actions.
problem Low-dimensional confounders and singleton actions in causal inference.
method Sequencification to transform data into sequences, enabling CI with complex confounders and sequential actions.
result AR model can estimate multiple causal quantities using a single model, simplifying inference and improving outcome prediction.
The Bradley-Terry model is a popular approach to describe probabilities of the possible outcomes when elements of a set are repeatedly compared with one another in pairs. It has found many applications including animal behaviour, chess ranking and multiclass classification. Numerous extensions of the basic model have a…
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.
A new Chinese Checkers agent combines heuristics, MCTS, and deep RL.
problem Challenging state-space and unbounded depth in Chinese Checkers.
method Combines heuristics, Monte Carlo Tree Search, and deep reinforcement learning.
result Competent agent reaches human player level.
AlphaZero's reward function is replaced with a total ordering, enabling self-play without balancing.
problem Learning optimal play in games without explicit reward balancing.
method Modified AlphaZero algorithm using only a total ordering of game outcomes.
result Comparable optimal play learned in a similar time frame without balancing.
AEC Games model represents software MARL environments better than POSGs.
problem POSGs are conceptually unsuitable for software MARL environments.
method Introduced AEC Games model as an equivalent to POSGs.
result AEC Games model is more representative of software MARL environments.
Hanabi game challenges AI with cooperative, imperfect information.
problem Developing AI capable of understanding others' beliefs and intentions.
method Introducing the Hanabi Learning Environment and experimental framework.
result Hanabi highlights the importance of theory of mind reasoning in AI.
Parallelizes MCTS for continuous domains using leaf and root parallelization.
problem Solving challenging tasks in continuous domains using MCTS.
method Extends existing parallelization strategies to continuous domains, focusing on leaf and root parallelization.
result Proposes two final selection strategies for continuous states in root parallelization.
Alpha Zero adapts to continuous action spaces for real-world tasks.
problem Real-world reinforcement learning domains often have continuous action spaces.
method Interleaves tree search and deep learning, extending Alpha Zero for continuous action spaces.
result Preliminary experiments on the Pendulum task show feasibility of the approach.
Study shows Elo models fail to accurately measure transitive strength in competitive games.
problem Elo models fail to correctly identify the transitive component in real-world competitive games.
method Investigated the challenge of identifying the transitive component in games, proposed an extension of the Elo score.
result Disc ranking system assigns two scores: skill and consistency.
New approach handles stochastic and partially-observable environments using discrete autoencoders and Monte Carlo tree search.
problem Challenges in planning for stochastic and partially-observable environments.
method Uses discrete autoencoders and a stochastic variant of Monte Carlo tree search.
result Significantly outperforms MuZero on stochastic chess and scales to DeepMind Lab.
MuZero visualizes its internal representations to stabilize planning.
problem Stability issues in MuZero's planning process.
method Visualized MuZero's latent representations and proposed regularization techniques.
result Action trajectories diverge between observation embeddings and internal state transitions, leading to instability.
New algorithm improves performance in nontransitive games.
problem Nontransitive games lack a clear winner.
method Geometric framework for agent objectives, PSRO_rN algorithm.
result PSRO_rN consistently outperforms alternatives in nontransitive games.
GPT learns a causal world model from token predictions, validated in game sequences.
problem Does GPT implicitly learn a causal world model from token predictions?
method Derived a causal interpretation of GPT's attention mechanism and proposed zero-shot causal structure learning.
result GPT can generate legal next moves with high confidence for sequences with encoded causal structures, but fails for illegal moves.
Paper introduces techniques to learn higher-order programs, improving predictive accuracy and reducing learning times.
problem Expressing and learning complex programs in ILP.
method Extending meta-interpretive learning to support higher-order definitions as background knowledge.
result Learning higher-order programs reduces hypothesis space and sample complexity, improving predictive accuracy and reducing learning times.
Equivariant MuZero improves generalization in procedurally generated environments.
problem Leveraging world models for robust generalization in real-world scenarios.
method Incorporates symmetries of the environment into MuZero's world-model architecture, making MuZero equivariant to certain groups of transformations.
result Improves data efficiency and generalization capabilities, demonstrated on procedurally generated MiniPacman and Chaser.
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.
This paper shows using classification instead of regression improves deep RL scalability.
problem Challenges in training value functions for large networks in deep RL.
method Used categorical cross-entropy loss instead of mean squared error regression.
result Significant improvements in performance and scalability across various domains.
HalluWorld benchmarks hallucinations in language models across diverse tasks.
problem Inconsistent benchmarks of hallucination in language models.
method Explicit reference-world formulation, synthetic and semi-synthetic environments, controlled variation of world complexity.
result Models struggle with perceptual hallucination but not multi-step state tracking.
With the scale of data growing every day, reducing the dimensionality (a.k.a. sketching) of high-dimensional data has emerged as a task of paramount importance. Relevant issues to address in this context include the sheer volume of data that may consist of categorical samples, the typically streaming format of acquisit…
Research tackles alliance formation in many-player zero-sum games, showing reinforcement learning fails but a contract mechanism can help.
problem Tackles the challenge of alliance formation in many-player zero-sum games.
method Demonstrates the social dilemma aspect of alliance formation, introduces a contract mechanism to augment reinforcement learning.
result Naïve reinforcement learning fails to form alliances, but a contract mechanism can help.
The question of aggregating pair-wise comparisons to obtain a global ranking over a collection of objects has been of interest for a very long time: be it ranking of online gamers (e.g. MSR's TrueSkill system) and chess players, aggregating social opinions, or deciding which product to sell based on transactions. In mo…
Quantum computing speeds up multi-period asset allocation.
problem High computational complexity in classic computing for multi-period asset allocation.
method Applied quantum computing to simulate multi-asset portfolio using historic data.
result Quantum computing offers significant advantages over classical computing in finance.
Hybrid approach reduces computation time and decoding complexity.
problem Straggling servers in distributed computing.
method Coded partial gradient computation (CPGC) that balances gradient accuracy and completion time.
result Reduces both computation time and decoding complexity.
The paper analyzes the pricing of a new compute futures asset.
problem Uncertainty in AI adoption and pricing of compute capital.
method An asset-pricing framework for compute futures, including synthetic futures pricing.
result Preliminary evidence suggests a positive compute risk premium.
Quantum computing offers energy savings over classical computing.
problem Energy efficiency in computing services.
method Cournot competition model constrained by energy usage.
result Quantum computing firms can outperform classical counterparts in energy efficiency.