arXiv research

Deep reinforcement learning (RL) has shown impressive results in a variety of domains, learning directly from high-dimensional sensory streams. However, when neural networks are trained in a fixed environment, such as a single level in a video game, they will usually overfit and fail to generalize to new levels. When R…

We applied Generative Adversarial Networks (GANs) to learn a model of DOOM levels from human-designed content. Initially, we analysed the levels and extracted several topological features. Then, for each level, we extracted a set of images identifying the occupied area, the height map, the walls, and the position of ga…

This paper improves level generation using VAEs for coherent, logically following segments.

TOAD-GAN generates coherent game levels from a single example.

GMVAEs cluster and generate game levels without labels.

Paper explores generalization of AID-based bi-level optimization methods.

Paper studies generic dynamics of MCFs with spherical singularities.

Minimal involutions generate a subgroup of nonorientable surfaces.

Music FaderNets learns high-level musical qualities from low-level attributes.

Generative model learns conditional distributions on collective variable levels.

New framework tackles bi-level optimization without LLS condition.

Study on Chern-Simons theory at generic levels, revealing universal resurgent structure.

The paper extends statistical inference methods for black-box generative models.

Trajectory-level supervision allows efficient offline reinforcement learning.

Proves convexity of level sets of general inverse σ_k equations.

For leveled spatial graphs, we find a surface embedding that allows cellular embedding.

The paper explores the geometry of level lines of quasiperiodic functions with many periods.

FRESH combines patient-level and aggregate-level data for better clinical decision making.

Segmentation of tumors in brain MRI images is a challenging task, where most recent methods demand large volumes of data with pixel-level annotations, which are generally costly to obtain. In contrast, image-level annotations, where only the presence of lesion is marked, are generally cheap, generated in far larger vol…

This paper shows how path spaces on two-level manifolds can be Hilbert manifold structures.

Generative Adversarial Networks (GANs) have obtained extraordinary success in the generation of realistic images, a domain where a lower pixel-level accuracy is acceptable. We study the problem, not yet tackled in the literature, of generating semantic images starting from a prior distribution. Intuitively this problem…

The paper calculates dimensions of higher Landau levels on compact manifolds.

We investigate how reinforcement learning can be used to train level-designing agents. This represents a new approach to procedural content generation in games, where level design is framed as a game, and the content generator itself is learned. By seeing the design problem as a sequential task, we can use reinforcemen…

BILBO optimizes bilevel problems without repeated lower-level optimizations.

Investigates a new measure PELVE_n for risk assessment.

We obtain a finite generating set for the level 2 twist subgroup of the mapping class group of a closed non-orientable surface. The generating set consists of crosscap pushing maps along non-separating two-sided simple loops and squares of Dehn twists along non-separating two-sided simple closed curves. We also prove t…

Quantum representations of mapping class groups are locally rigid at prime levels.

It is known that the level $2$ principal congruence subgroup of $GL(n;\mathbb{Z})$ has a finite generating set. In this paper, we give a finite presentation of the level $2$ principal congruence subgroup of $GL(n;\mathbb{Z})$.

We present a domain-general account of causation that applies to settings in which macro-level causal relations between two systems are of interest, but the relevant causal features are poorly understood and have to be aggregated from vast arrays of micro-measurements. Our approach generalizes that of Chalupka et al. (…

A Python tool generates synthetic data for cluster analysis from high-level descriptions.

We construct a minimal generating set of the level 2 mapping class group of a nonorientable surface of genus $g$, and determine its abelianization for $g\ge4$.

Hierarchical analysis is considered and a multilevel model is presented in order to explore causality, chance and complexity in financial economics. A coupled system of models is used to describe multilevel interactions, consistent with market data: the lowest level is occupied by agents generating the prices of indivi…

2-level SLOPE improves high-dimensional inference with fewer hyperparameters.

Program synthesis of general-purpose source code from natural language specifications is challenging due to the need to reason about high-level patterns in the target program and low-level implementation details at the same time. In this work, we present PATOIS, a system that allows a neural program synthesizer to expl…

The study explores the structure of mapping class groups of non-orientable surfaces.

New PCGML approach generates novel game content across multiple platformer domains.

Proposes MGPLL for PL learning with non-random noise.

FIGARO generates symbolic music with fine-grained control.

We present a novel method for hierarchical topic detection where topics are obtained by clustering documents in multiple ways. Specifically, we model document collections using a class of graphical models called hierarchical latent tree models (HLTMs). The variables at the bottom level of an HLTM are observed binary va…

The clusters of a distribution are often defined by the connected components of a density level set. However, this definition depends on the user-specified level. We address this issue by proposing a simple, generic algorithm, which uses an almost arbitrary level set estimator to estimate the smallest level at which th…

Researchers infer firm-level supply chain networks from sector-level data to assess systemic risk.

Self-explaining models are models that reveal decision making parameters in an interpretable manner so that the model reasoning process can be directly understood by human beings. General Linear Models (GLMs) are self-explaining because the model weights directly show how each feature contributes to the output value. H…

Introduces six levels of privacy for financial synthetic data.

We obtain a finite set of generators for the level 2 mapping class group of a closed nonorientable surface of genus $g\ge 3$. This set consists of isotopy classes of Lickorish's Y-homeomorphisms also called crosscap slides.

Forecasts of multivariate probability distributions are required for a variety of applications. Scoring rules enable the evaluation of forecast accuracy, and comparison between forecasting methods. We propose a theoretical framework for scoring rules for multivariate distributions, which encompasses the existing quadra…

Network quantization is an effective solution to compress deep neural networks for practical usage. Existing network quantization methods cannot sufficiently exploit the depth information to generate low-bit compressed network. In this paper, we propose two novel network quantization approaches, single-level network qu…

Deep Reinforcement Learning (DRL) has shown impressive performance on domains with visual inputs, in particular various games. However, the agent is usually trained on a fixed environment, e.g. a fixed number of levels. A growing mass of evidence suggests that these trained models fail to generalize to even slight vari…

We introduce a novel approach to graph-level representation learning, which is to embed an entire graph into a vector space where the embeddings of two graphs preserve their graph-graph proximity. Our approach, UGRAPHEMB, is a general framework that provides a novel means to performing graph-level embedding in a comple…