WILD-SCAV benchmarks AI in complex 3D FPS environments.
problem Lack of complexity and diversity in RL environments.
method Developed a 3D open-world FPS game environment.
result Demonstrates effectiveness in benchmarking RL algorithms.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,922 papers · 148 categories
Trend · papers per month
48 results for “FPS environments”
Model uses HS-FP framework for South African asset allocation.
problem Develops a flexible non-parametric asset allocation model for South African markets.
method Historical Simulation with Flexible Probabilities (HS-FP) framework, using relative entropy for distribution estimation.
result HS-FP model outperforms classic MVO and EW benchmarks in out-of-sample performance.
The paper investigates the effectiveness of reusing experience in Deep Q-Learning for FPS environments.
problem The high number of interactions required for reinforcement learning limits its practicality.
method The authors test the effectiveness of applying learning update steps multiple times per environmental step in the VizDoom environment.
result Updating learning steps less frequently than every 4th environmental step does not improve performance and can degrade performance.
FP-UCB algorithm achieves bounded regret for finitely parameterized multi-armed bandits.
problem Finitely parameterized multi-armed bandits with unknown but known parameter set.
method FP-UCB algorithm using structural information about the parameter set.
result FP-UCB achieves bounded regret under structural condition, logarithmic otherwise.
We consider vector fixed point (FP) equations in large dimensional spaces involving random variables, and study their realization-wise solutions. We have an underlying directed random graph, that defines the connections between various components of the FP equations. Existence of an edge between nodes i, j implies the …
Study on homological Dehn functions of groups of type .
problem Understanding the homological Dehn functions of groups of type .
method Proved foundational results, studied homological Dehn functions of Leary's groups, and provided methods to obtain groups with specific homological Dehn functions.
result Found groups of type with quartic homological Dehn function and unsolvable word problem.
Uncountably many groups of type math.GR
We construct uncountably many discrete groups of type ; in particular we construct groups of type that do not embed in any finitely presented group. We compute the ordinary, - and compactly-supported cohomology of these groups. For each we construct a closed aspherical -manifold that admit…
FP uses random projections to train networks without feedback, achieving comparable performance to backpropagation.
problem Training neural networks without feedback from downstream layers.
method Forward Projection (FP) method that uses randomised nonlinear projections and closed-form regression.
result FP achieves comparable generalisation to backpropagation methods with a single forward pass, offering significant speedup.
GGFPS improves model performance by sampling molecules more efficiently.
problem Improving model performance and reducing data costs in chemistry problems.
method Gradient-Guided Furthest Point Sampling (GGFPS) that leverages molecular force norms.
result GGFPS leads to superior data efficiency and model robustness compared to other sampling methods.
In this paper we create many examples of hyperbolic groups with subgroups satisfying interesting finiteness properties. We give the first examples of subgroups of hyperbolic groups which are of type but not finitely presented. We give uncountably many groups of type with similar properties to those subgro…
Neural MMO v1.3: A Massively Multiagent Game Environment for Training and Evaluating Neural Networkscs.LG
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.
The study examines geodesic orbit Finsler spaces with non-negative flag curvature and (FP) condition, proving they are compact.
problem Characterizing geodesic orbit Finsler spaces with specific curvature conditions.
method Analyzes the interaction between geodesic orbit property and flag curvature conditions.
result Compactness of geodesic orbit Finsler spaces with non-negative flag curvature and (FP) condition.
Recent developments in deep reinforcement learning have enabled the creation of agents for solving a large variety of games given a visual input. These methods have been proven successful for 2D games, like the Atari games, or for simple tasks, like navigating in mazes. It is still an open question, how to address more…
Latent-space metrics for Complex-Valued VAE out-of-distribution detection under radar cluttereess.SP
Study complex-valued VAEs for radar OOD detection.
problem Detecting out-of-distribution signals in complex radar environments.
method Proposed and compared several detection metrics for CVAE.
result CVAE-MSE and latent-based scores outperform ANMF-Tyler.
New method improves feature selection by integrating stability paths.
problem Improving feature selection with tighter false positive control.
method Integrating stability paths to strengthen theoretical bounds on E(FP).
result Significantly more true positives with same E(FP) control.
Popular deep neural networks (DNNs) spend the majority of their execution time computing convolutions. The Winograd family of algorithms can greatly reduce the number of arithmetic operations required and is present in many DNN software frameworks. However, the performance gain is at the expense of a reduction in float…
High-throughput 3D control training system achieves 100,000 FPS.
problem Lack of efficient, single-machine reinforcement learning systems.
method Sample Factory combines asynchronous sampling and off-policy correction.
result Achieves 100,000 FPS on 3D control problems without sacrificing sample efficiency.
L-CNNs approximate gauge actions, revealing fixed points with no lattice artifacts.
problem Approximating gauge actions with lattice artifacts.
method Lattice gauge-equivariant convolutional neural networks (L-CNNs).
result L-CNNs provide fixed point actions with no lattice artifacts.
Formanek and Procesi have demonstrated that Aut(F_n) is not linear for n >2. Their technique is to construct nonlinear groups of a special form, which we call FP-groups, and then to embed a special type of automorphism group, which we call a poison group, in Aut(F_n), from which they build an FP-group. We first prove t…
Since machine learning models have been applied to neuroimaging data, researchers have drawn conclusions from the derived weight maps. In particular, weight maps of classifiers between two conditions are often described as a proxy for the underlying signal differences between the conditions. Recent studies have however…
Previously one of the authors constructed uncountable families of groups of type and of -dimensional Poincaré duality groups for each . We strengthen these results by showing that these groups comprise uncountably many quasi-isometry classes. We deduce that for each there are uncountably many…
In this paper, we introduce the flag-wise positively curved condition for Finsler spaces (the (FP) Condition), which means that in each tangent plane, we can find a flag pole in this plane such that the corresponding flag has positive flag curvature. Applying the Killing navigation technique, we find a list of compact …
GAN-FP uses GANs to predict equipment failures from imbalanced data.
problem Accurately predicting equipment failures with limited data and high imbalance.
method GAN-FP employs two GAN networks to generate and classify imbalanced data, optimizing a weighted loss objective and a consistency GAN.
result GAN-FP outperforms traditional methods in imbalanced failure prediction.
The monotonicity of the Franz-Parisi potential is equivalent with Low-degree MMSE lower boundsmath.ST
New work shows FP potential monotonicity equals low-degree polynomial estimators limits.
problem Establishing a precise mathematical relationship between statistical physics and polynomial estimators limits.
method Analyzing Gaussian additive models (GAMs) to show FP potential monotonicity equals low-degree polynomial estimators limits.
result For a broad family of Gaussian additive models, the power of low-degree polynomials is equivalent to the monotonicity of the annealed FP potential.
AI agent plays CSGO deathmatch with human-like style.
problem Lack of API for CSGO limits data for reinforcement learning.
method Behavioural cloning on large noisy and expert datasets.
result Matches human difficulty level in deathmatch mode.
This paper extends FP's method to complex hyperbolic branched covers to find Einstein metrics.
problem Finding Einstein metrics on non-locally symmetric manifolds.
method Generalized FP's construction to complex hyperbolic branched covers.
result Yields a negatively curved Einstein metric that asymptotically approaches GH's metric.
The presence of a sparse "truth" has been a constant assumption in the theoretical analysis of sparse PCA and is often implicit in its methodological development. This naturally raises questions about the properties of sparse PCA methods and how they depend on the assumption of sparsity. Under what conditions can the r…
FP-BMA improves generalization by encouraging flat posteriors in Bayesian Model Averaging.
problem Lack of flat posterior in approximate Bayesian inference methods hinders effective Bayesian Model Averaging.
method Proposes Flat Posterior-aware Bayesian Model Averaging (FP-BMA) and Flat Posterior-aware Bayesian Transfer Learning schemes.
result FP-BMA successfully captures flat posteriors, improving generalization performance.
Develops a neural network approach to solve inverse stochastic problems from particle observations.
problem Inference of Fokker-Planck equation coefficients from sparse particle data.
method Physics-informed neural networks (PINNs) with Kullback-Leibler divergence loss.
result Simultaneous inference of Fokker-Planck equation and multi-dimensional PDF from few particle observations.
The paper classifies PD_4-complexes based on their fundamental group properties.
problem Understanding the structure of PD_4-complexes based on their fundamental group properties.
method Analyzing the fundamental group and its modules to classify PD_4-complexes.
result The classification of PD_4-complexes based on their fundamental group properties.
Meta-learning improves image segmentation performance.
problem Improving image segmentation accuracy using meta-learning.
method Extending FOMAML and Reptile to image segmentation, using EfficientLab architecture, and leveraging test error definition.
result Meta-learned initializations provide value for few-shot image segmentation but are quickly matched by conventional transfer learning.
One of the key challenges in predictive maintenance is to predict the impending downtime of an equipment with a reasonable prediction horizon so that countermeasures can be put in place. Classically, this problem has been posed in two different ways which are typically solved independently: (1) Remaining useful life (R…
Optimized Franz-Parisi criterion matches SQ lower bounds for various statistical models.
problem Understanding computational hardness in statistical inference.
method Proposed and refined Franz-Parisi criterion, established equivalence with SQ lower bounds.
result Optimized Franz-Parisi criterion is equivalent to Statistical Query (SQ) lower bounds.
Hougthon's groups H_n is a family of groups where each H_n consists of `translations at infinity' on n rays of discrete points emanating from the origin on the plane. Brown shows H_n has type FP_n-1 but not FP_n by constructing infinite dimensional cell complex on which H_n acts with certain conditions. We modify his i…
A novel score-based method solves high-dimensional Fokker-Planck equations with improved accuracy and speed.
problem High-dimensional Fokker-Planck equations suffer from the curse of dimensionality, leading to numerical errors and slow sampling.
method Score-based Physics-Informed Neural Networks (PINNs) that fit the score function in SDEs, using three methods: Score Matching, Sliced Score Matching, and Score-PINN.
result The score-based method outperforms traditional Monte Carlo and vanilla PINNs in high-dimensional settings, offering faster sampling and reduced errors.
Enhanced ontology learning from text improves question-answering systems.
problem Improving ontology learning from unstructured text for better question-answering systems.
method Heuristically modified FP-Tree with DFA for concept extraction and frequent pattern mining for ontology learning.
result Our approach significantly improves question-answering system performance, answering 80% of questions compared to 28.4% with Text2Onto.
We determine when an arithmetic subgroup of a reductive group defined over a global function field is of type FP_\infty by comparing its large-scale geometry to the large-scale geometry of lattices in real semisimple Lie groups.
Neural Galerkin Normalizing Flows for Bayesian Inference of Diffusions with Inaccessible Boundariescs.LG
New method learns diffusion transition density for Bayesian inference.
problem Bayesian inference on diffusions with inaccessible boundaries.
method Neural Galerkin framework to solve FP equation with Dirac mass.
result Approximates likelihood function for efficient posterior sampling.
Winograd convolution is widely used in deep neural networks (DNNs). Existing work for DNNs considers only the subset Winograd algorithms that are equivalent to Toom-Cook convolution. We investigate a wider range of Winograd algorithms for DNNs and show that these additional algorithms can significantly improve floating…
If S is a subgroup of a direct product of two limit groups, and S is of type FP(2) over the rationals, then S has a subgroup of finite index that is a direct product of at most two limit groups.
We show that the Basilica Thompson group introduced by Belk and Forrest is not finitely presented, and in fact is not of type FP_2. The proof involves developing techniques for proving non-simple connectedness of certain subcomplexes of CAT(0) cube complexes.
We study the asymptotic growth of homology groups and the cellular volume of classifying spaces as one passes to normal subgroups of increasing finite index in a fixed finitely generated group , assuming . We focus in particular on finitely presented residually free groups, calculating thei…
New optimization method improves AUC for binary classification and changepoint detection.
problem Non-convex AUC and sub-optimal points in ROC curves.
method AUM (Area Under Min(FP, FN)) surrogate loss function based on sorting and summing ROC curve points.
result AUM minimization learning algorithm improves AUC and speeds up compared to previous methods.
New activation networks improve model efficiency and performance.
problem Creating hardware-efficient deep learning models.
method Restructurable Activation Networks (RANs) with RAN-explicit and RAN-implicit methods.
result RANs achieve state-of-the-art results with improved hardware efficiency.
Considered as a data-driven approach, Fingerprinting Localization Solutions (FPSs) enjoy huge popularity due to their good performance and minimal environment information requirement. This papers addresses applications of artificial intelligence to solve two problems in Received Signal Strength Indicator (RSSI) based F…
If are limit groups and is of type $\FP_n(\mathbb Q)$ then contains a subgroup of finite index that is itself a direct product of at most limit groups. This settles a question of Sela.
As an application of `reverse engineering' technique introduced by R. Fintushel, D. Park and R. Stern \cite{FPS}, we construct an infinite family of fake (2n+2l-1)CP^2#(2n+4l-1)(-CP^2)'s for all n \ge 0, l \ge 1.
This paper presents the first two editions of Visual Doom AI Competition, held in 2016 and 2017. The challenge was to create bots that compete in a multi-player deathmatch in a first-person shooter (FPS) game, Doom. The bots had to make their decisions based solely on visual information, i.e., a raw screen buffer. To p…