Paper applies NFSP to Mini-RTS, a small RTS game.
problem Applying AI to RTS games due to their multi-agent nature.
method Neural Fictitious Self-Play (NFSP) combined with policy gradient reinforcement learning.
result NFSP can be effectively applied to Mini-RTS and improved with pretraining.
This study compares global vs local observation and action representations for DRL in RTS games.
problem Improving Deep Reinforcement Learning performance in RTS games.
method Comparing two observation and action representations in μRTS.
result Local representation outperforms global representation in resource harvesting tasks.
DefogGAN predicts hidden RTS game information to aid strategic decision-making.
problem Predicting hidden information in real-time strategy games like StarCraft.
method Conditional Generative Adversarial Network (GAN) with pyramidal reconstruction loss.
result DefogGAN predicts enemy buildings and combat units as accurately as professional players.
Action guidance helps agents learn true objectives in games with sparse rewards.
problem Training agents in games with sparse rewards requires significant exploration.
method Action guidance, a novel technique that combines exploration with reward shaping.
result Action guidance enables agents to optimize true objectives efficiently.
Many complex domains, such as robotics control and real-time strategy (RTS) games, require an agent to learn a continuous control. In the former, an agent learns a policy over Rd and in the latter, over a discrete set of actions each of which is parametrized by a continuous parameter. Such problems are natu…
Agents struggle with solving tasks in new environments, but new models improve performance.
problem Rapid task-solving in novel environments.
method Developed EPNs to enable deep RL agents to plan over gathered knowledge.
result EPNs enable deep RL agents to excel at RTS, outperforming baselines by factors of 2-3.
Neural MMO simulates MMOs to study multiagent intelligence.
problem Limited research environments for multiagent intelligence.
method Developed a new game environment inspired by MMOs.
result Standard methods can learn interesting behaviors in MMOs.
Defines Ribaucour-type surfaces and their properties.
problem Defines a new class of surfaces related to the Élie Cartan problem.
method Introduces a new class of surfaces and provides a Weierstrass type representation.
result Every compact and connected RT-surface is a sphere centered at the origin.
The study examines Ricci solitons and curvature inheritance on Robinson-Trautman spacetimes.
problem Investigating Ricci solitons and curvature inheritance in Robinson-Trautman spacetimes.
method Analyzing the existence of Ricci solitons and curvature inheritance properties on Robinson-Trautman spacetimes.
result Robinson-Trautman spacetimes admit various types of Ricci solitons and curvature inheritance.
Proposes RT decomposition for better multi-relational link prediction.
problem Improving multi-relational link prediction in knowledge graphs.
method Relational Tucker3 (RT) decomposition, decouples entity and relation embeddings, allows parameter sharing, and learns sparsity patterns.
result RT decomposition can outperform existing sparse models in multi-relational link prediction.
Reinforcement Learning (RL) is a research area that has blossomed tremendously in recent years and has shown remarkable potential for artificial intelligence based opponents in computer games. This success is primarily due to vast capabilities of Convolutional Neural Networks (ConvNet), enabling algorithms to extract u…
RT estimators provide unbiased gradients for expensive loops or approximations.
problem Expensive optimization problems with inner loops or approximations.
method Randomized telescoping (RT) gradient estimators.
result RT estimators achieve unbiased gradients independent of loop length or approximation accuracy.
We calculate the RT-invariants of all oriented Seifert manifolds directly from surgery presentations. We work in the general framework of an arbitrary modular category as in [V. G. Turaev, Quantum invariants of knots and 3--manifolds, de Gruyter Stud. Math. 18, Walter de Gruyter (1994)], and the invariants are expresse…
Expanding models in neural fictitious play improves reinforcement learning efficiency and robustness.
problem Forgetting old opponents after training new ones in reinforcement learning.
method Train a single model with sub-models and a selector, expanding the model with new sub-models and updating the selector to maintain a behavior strategy.
result Improves learning efficiency and robustness of neural fictitious play.
In the top-down approach to multi-name credit modeling, calculation of singe name sensitivities appears possible, at least in principle, within the so-called random thinning (RT) procedure which dissects the portfolio risk into individual contributions. We make an attempt to construct a practical RT framework that enab…
Introduces Conditional Action Trees to simplify RL action spaces.
problem Challenges in RL with large, complex action spaces.
method Structures action spaces and reduces complexity through Conditional Action Trees.
result Demonstrates effectiveness in reducing action space and improving decision making.
Reinforcement learning improves trading performance on stock exchanges.
problem Optimizing trading strategies on stock exchanges using machine learning.
method Markov model, asynchronous advantage actor-critic method, neural networks, recurrent layers.
result Best trading strategy for RTS Index futures achieved a 66% annual profit.
Let $\1$ and $\2$ be $\s$ domains in $\Cn$ and $f: \1 \rt \2$ an isometry for the Kobayashi or Carathéodory metrics. Suppose that f extends as a C1 map to $ \bar \om_1$. We then prove that $f|_{\partial \1}: \partial \1 \rt \partial \2$ is a CR or anti-CR diffeomorphism. It follows that $\1$ and $\2$ must be bihol…
Extends optimal regularity and Uhlenbeck compactness to non-Riemannian manifolds.
problem Establishing optimal regularity and compactness for connections on vector bundles over non-Riemannian manifolds.
method Proofs based on RT-equations for connections with Lp curvature, extending to non-compact gauge groups. result Removes singularities at GR shock waves, ensuring existence of geodesics and coordinates.
Let X be a locally symmetric space associated to a reductive algebraic group G defined over Q. L-modules are a combinatorial analogue of constructible sheaves on the reductive Borel-Serre compactification of X; they were introduced in [math.RT/0112251]. That paper also introduced the micro-support of an L-module, a com…
Finite image of Reidemeister torsion for a specific 3-manifold splice.
problem Determining the finiteness of the Reidemeister torsion set for 3-manifolds.
method Analysis of character varieties and A-polynomials of knots.
result The set of values of the SL(2,C)-Reidemeister torsion is finite for splices of certain knots.
A new statistical concept, lepto-variance, is defined for stock returns using Regression Trees.
problem Understanding the underlying structure of stock returns using statistical methods.
method Defining lepto-variance as the variance that cannot be removed by any regression tree of a specific depth and analyzing stock returns with 1- and 2-bit Regression Trees.
result Lepto-variance quantifies the resolving power of Regression Trees for stock returns, decomposing total variance into lepto-variance and macro-variance.
JSRT improves regression tree performance by incorporating global node information.
problem Regression tree performance relies on local node means, ignoring global node information.
method Proposes JSRT by integrating global mean information from different nodes.
result Demonstrates superior performance and efficiency compared to other regression tree methods.
This note provides an error bound for the Hartman-Watson integral's leading term.
problem Bounding the error of the leading term of the Hartman-Watson integral.
method Asymptotic expansion analysis focusing on the regime rt=ρ constant. result The error term is bounded uniformly as ∣ϑ(t,ρ)∣≤701t. Automates quality control for synthetic CTs generated from MR images.
problem Prevent downstream errors in RT treatment planning from synthetic CTs.
method Ensemble of sCT generators and uncertainty measure based on their disagreement.
result Uncertainty measure can detect input images outside expected MR distribution and sCT images with potential errors.
Extends optimal regularity and compactness to vector bundles over non-Riemannian manifolds.
problem Optimal regularity and compactness for connections on vector bundles.
method Derive RT-equations, establish existence theory, handle curvature up to L1. result Optimal regularity and compactness extended to vector bundles over non-Riemannian manifolds.
Unified framework for response-adaptive targeting in multi-treatment experiments
problem Improving ethical and statistical efficiency in multi-treatment clinical trials
method Response-adaptive targeting strategies
result Unified framework for α-Rebalancing Targeting Strategies (αRTS) Let (M,g) be a two-dimensional compact boundaryless Riemannian manifold with nonpostive curvature, then we shall give improved estimates for the L2-norms of the restrictions of eigenfunctions to unit-length geodesics, compared to the general results of Burq, Gérard and Tzvetkov \cite{burq}. By earlier results of B…
We propose a mathematical procedure for finding informed traders in ultra-high frequency trading. We wrote it as Vector ARMA and found condition of its stationarity. For the price exposure complied with ARMA(1,2) we proved that underlying asset price difference can be derived as ARMA(1,1) process. For validation of the…
The Ryu-Takayanagi (RT) formula relates the entanglement entropy of a region in a holographic theory to the area of a corresponding bulk minimal surface. Using the max flow-min cut principle, a theorem from network theory, we rewrite the RT formula in a way that does not make reference to the minimal surface. Instead, …
Paper finds essential regularity in singular connections.
problem Determining if singularities in connections are removable or essential.
method Introduces RT-equations and a procedure to lift connections to essential regularity.
result A computable procedure to lift connections to essential regularity.
Proposes RPG-RT for red-teaming T2I models without internal access.
problem Evaluating T2I models' security through red-teaming is challenging due to their closed-source nature and unknown defense mechanisms.
method Integrates LLM and rule-based preference modeling to dynamically adapt to unknown defense mechanisms.
result Demonstrates superior and practical approach for red-teaming T2I models.
We present a numerical framework for approximating unknown governing equations using observation data and deep neural networks (DNN). In particular, we propose to use residual network (ResNet) as the basic building block for equation approximation. We demonstrate that the ResNet block can be considered as a one-step me…
Using elementary comparison geometry, we prove: Let (M,g) be a simply-connected complete Riemannian manifold of dimension ≥3. Suppose that the sectional curvature K satisfies −1−s(r)≤K≤−1, where r denotes distance to a fixed point in M. If $\lim_{r \rt \infty} e^{2r}s(r) =0$, then (M,g) has to…
Two new estimators improve VAE training for hierarchical and prior parameters.
problem Efficient gradient estimation for VAEs with hierarchical and prior parameters.
method Developed two generalizations of Doubly-Reparameterized Gradient Estimators (DReGs) for VAEs.
result Improved training of conditional and hierarchical VAEs on image modeling tasks.
The main results of A. Zorich and I. Dynnikov about plane sections of periodic surfaces are extended to the PL case. As an application, the Stereographic Map of a truncated octahedron, extended to the whole $\Rt$ by periodicity, is analyzed numerically.
The expected low market penetration of connected vehicles (CVs) in the near future could be a constraint in estimating traffic flow parameters, such as average travel speed of a roadway segment and average space headway between vehicles from the CV broadcasted data. This estimated traffic flow parameters from low penet…
Noisy Pooled PCR tests large groups more efficiently.
problem Efficiently test large populations for viral infections.
method Converts group testing to a linear inverse problem with a message passing algorithm.
result Estimates patient illness status with fewer pooled measurements.
Authors develop a new theory to smooth spacetime connections and remove singularities in GR shock waves.
problem Singularities in General Relativity shock waves and optimal regularity of spacetime connections.
method Established a general multi-dimensional existence theory for Reintjes-Temple equations using elliptic regularity in Lp spaces. result Regularities of GR shock waves can always be removed by coordinate transformations, extending Uhlenbeck compactness to Lorentzian geometry.
Study improves CAD diagnosis accuracy by selecting significant features.
problem Improving accuracy of CAD diagnosis through feature selection.
method Integrated machine learning approach using random trees (RTs), C5.0, SVM, and CHAID.
result Random trees model outperforms other models in CAD diagnosis.
Paper introduces new indicators for forecasting crude oil prices using short news headlines.
problem Forecasting crude oil prices from short, noisy news headlines using LDA.
method Developed two novel indicators for topic and sentiment from short text data, and applied AdaBoost.RT.
result AdaBoost.RT with the proposed indicators outperforms benchmarks in crude oil forecasting.
Satake has constructed compactifications of symmetric spaces D=G/K which (under a condition called geometric rationality by Casselman) yield compactifications of the corresponding locally symmetric spaces. The different compactifications depend on the choice of a representation of G. One example is the Baily-Borel-Sata…
In the present paper we develop a framework in which questions of quantum ergodicity for operators acting on sections of hermitian vector bundles over Riemannian manifolds can be studied. We are particularly interested in the case of locally symmetric spaces. For locally symmetric spaces, we extend the recent construct…
ClimART dataset benchmarks ML emulators for atmospheric RT in climate models.
problem Lack of a comprehensive dataset and standardized practices for ML benchmarking in climate models.
method Builds ClimART, a large dataset with over 10 million samples, and presents novel baselines.
result Indicates shortcomings of prior datasets and network architectures.
Deep learning aligns GC-MS peaks for biomarker discovery.
problem Aligning retention times of GC-MS peaks across different samples.
method ChromAlignNet, a deep learning model for peak alignment.
result ChromAlignNet outperforms existing methods on complex data sets.
The paper extends Hawking's singularity theorem to metrics with Hölder continuity and bounded curvature.
problem Proving singularity theorems for metrics with low regularity.
method Combining elliptic RT-equations for metric regularisation and manifold convolution for curvature refinement.
result Establishes globally hyperbolic and timelike incompleteness for metrics with Hölder continuity and bounded curvature.
Machine learning model diagnoses COVID-19 from routine blood tests.
problem Difficulty in diagnosing COVID-19 due to inconsistent blood parameter changes.
method Constructed a machine learning model using 5,333 patients with various infections and 160 COVID-19-positive patients.
result Cross-validated AUC of 0.97, sensitivity of 81.9%, specificity of 97.9%.
Study open 3-manifolds as sums of closed ones, finding a classification.
problem Classifying open 3-manifolds that are sums of closed 3-manifolds.
method Introduced topological invariants, classified when finitely many summands up to diffeomorphism.
result Unified classification of open 3-manifolds and closed 3-manifolds.