Unified policy controls diverse agents through modular neural networks.
problem Learning control policies for various agent morphologies.
method Shared Modular Policies (SMP) with decentralized control and message passing.
result A single modular policy controls multiple agent morphologies.
This paper studies how modular agents can learn to control complex morphologies.
problem Contemporary sensorimotor learning starts with existing complex agents, but this paper explores learning from primitive, modular agents.
method A collection of primitive agents learns to dynamically self-assemble into composite bodies and coordinate their behavior to control these bodies.
result Dynamic and modular agents demonstrate better generalization to test-time changes in both environment and agent structure.
MSPM uses modular agents to manage financial portfolios efficiently.
problem Scalability and reusability issues in RL-based financial portfolio management.
method Modular design with Evolving Agent Module (EAM) and Strategic Agent Module (SAM).
result MSPM improves profit accumulation by at least 186.5% compared to CRP.
A network of spiking agents learns complex tasks using global reward signals.
problem Solving complex reinforcement learning tasks.
method A hierarchical network of GLM spiking agents, each modulating its firing policy based on local and global reward signals.
result A network of spiking agents can learn complex action representations to solve RL tasks.
Hierarchical Modular Reinforcement Learning (HMRL), consists of 2 layered learning where Profit Sharing works to plan a prey position in the higher layer and Q-learning method trains the state-actions to the target in the lower layer. In this paper, we expanded HMRL to multi-target problem to take the distance between …
An artificial agent for financial risk and returns' prediction is built with a modular cognitive system comprised of interconnected recurrent neural networks, such that the agent learns to predict the financial returns, and learns to predict the squared deviation around these predicted returns. These two expectations a…
SLM Lab is a framework for reproducible RL research with modular algorithms.
problem Reproducibility in deep reinforcement learning.
method Modular software framework for RL algorithms, synchronous/asynchronous execution, hyperparameter search, result analysis.
result Comprehensive benchmark and novel RL algorithms (e.g., discrete-AC variant, hybrid training method).
Modular method predicts motion in crowded scenes using learned environment models.
problem Predicting motion in dynamic, crowded environments.
method Modular model of spatial and dynamic aspects, unsupervised adaptation to new tasks.
result Comparable performance to state-of-the-art, transferable across tasks.
Modular RL modules solve complex 3D Sokoban tasks.
problem Solving complex, integrated tasks combining visual, physical, and abstract reasoning.
method Compose RL modules in a sense-plan-act hierarchy, using only model-free methods.
result Modular RL outperforms state-of-the-art monolithic RL on Mujoban.
Dynamic information balancing reduces catastrophic forgetting in modular neural networks.
problem Catastrophic forgetting in neural networks when learning multiple tasks.
method Dynamic Information Balancing (DIB) using reinforcement learning to adaptively route inputs based on module information load.
result DIB combined with EWC regularization outperforms models with similar capacity and EWC regularization.
Decomposes game environments into controllable and non-controllable parts for faster learning.
problem Difficulties in end-to-end learning for complex environments.
method Modularization of the environment into controllable and non-controllable parts, using supervised and reinforcement learning.
result Human-level performance achieved in 10-15 minutes of game time with proper decomposition.
NeuroMAS treats multi-agent systems as neural networks for scalable, trainable coordination.
problem Designing multi-agent systems as hand-designed workflows is inefficient and inflexible.
method NeuroMAS treats multi-agent systems as a neural network architecture with reinforcement learning for scalable coordination.
result NeuroMAS improves significantly over multi-agent baselines and can be scaled progressively.
A reinforcement learning framework for Mars rover control using temporal logic.
problem Sparse rewards in continuous-state continuous-action MDPs with high-level temporal structures.
method Actor-critic, model-free, online RL framework with modular DDPG architecture.
result Success rate of synthesised policy in Mars rover experiment.
A decentralized approach for agents to learn and optimize collectively.
problem Challenges in coordinating non-cooperative agents to solve complex sequential decision problems.
method Designing a learning environment where agents learn by trading and optimizing local objectives, leading to a Nash equilibrium.
result Decentralized reinforcement learning algorithms that can handle various decision-making scenarios.
RL algorithm optimizes jet grooming for collider experiments.
problem Improving jet mass resolution in boosted objects.
method Deep RL agent trained on signal and background samples.
result RL-derived grooming algorithm matches state-of-the-art techniques.
New AI governance framework tackles risks in finance.
problem Risks from evolving AI models in finance.
method Agent-based framework with modular governance architecture.
result Controls quarantine harmful behavior in real time.
New RL environments help AI learn causal relationships from visual data.
problem Learning causal relationships from visual data for AI agents.
method Designing benchmark RL environments and evaluating representation learning algorithms.
result Explicitly incorporating structure and modularity improves causal induction in model-based RL.
New theorems show agents need specific internal structures to perform well under uncertainty.
problem How do agents need to be structured to perform well under uncertainty?
method Proved selection theorems showing strong task performance forces specific internal structures.
result Strong task performance forces world models, belief-like memory, and persistent regime-tracking variables.
SIMPOL solves complex economic models using numerical methods.
problem Optimizing consumption and savings under uncertainty.
method SIMPOL uses a modular numerical framework combining policy iteration and finite difference schemes.
result SIMPOL produces solutions consistent with economic and mathematical theory.
HiDe learns hierarchical control for complex tasks by separating planning and control.
problem Solving long horizon control tasks with generalization to unseen scenarios.
method Functional decomposition of state-action spaces, RL-based planner, modular transfer of policy layers.
result Generalizes across unseen test environments and scales to longer horizons.
Generative AI agents improve ERP systems by automating complex financial tasks.
problem Static, rule-based workflows limit adaptability and intelligence in ERP systems.
method Introducing Generative Business Process AI Agents (GBPAs) that integrate generative AI with business process modeling and multi-agent orchestration.
result GBPAs achieve up to 40% reduction in processing time and 94% drop in error rate.
We find and propose an explanation for a large variety of modularity-related symmetries in problems of 3-manifold topology and physics of 3d N=2 theories where such structures a priori are not manifest. These modular structures include: mock modular forms, SL(2,Z) Weil representations, quantum mo…
The study proves necessary conditions for robust decision-making in uncertain environments.
problem Conditions for robust decision-making in uncertain environments.
method Quantitative selection theorems and binary betting decisions.
result World models, belief-like memory, and persistent variables are necessary for strong task performance.
PandaAI: A practical agent for neuro-symbolic data analysis and decision-making in finance
problem Sequential decision-making in finance
method Leveraging LLMs for market regime modeling and constrained alpha generation
result PandaAI achieves higher Rank IC and lower maximum drawdown
Researchers found the global topology of the Eisenstein-Picard modular surface.
problem Understanding the global topology of the Eisenstein-Picard modular surface.
method Quotient space of the complex hyperbolic plane by the modular group.
result Determined the global topology of the Eisenstein-Picard modular surface as a 4-orbifold.
Study modular surfaces in Lorentz-Minkowski 3-space, classifying and analyzing their curvature and applications.
problem Understanding the curvature properties of modular surfaces in Lorentz-Minkowski space.
method Analyzing the sign of Gaussian and mean curvature, classifying surfaces, and applying to conformal field theories.
result Complete classification of zero Gaussian curvature modular surfaces and non-existence of non-planar maximal modular surfaces.
Modular neural networks generalize better with less data.
problem Theoretical and practical understanding of how modularity improves neural network generalization.
method Theoretical analysis of sample complexity, development of a novel learning rule.
result Modular networks require fewer samples to generalize compared to nonmodular networks, especially in high-dimensional tasks.
This review establishes a taxonomy for modular neural networks.
problem Scaling ANNs for complex and multi-disciplinary problems.
method Systematic analysis of modularization techniques in MNNs.
result A universal framework for studying MNNs.
Study modular forms over Γ^0(2) and anomaly cancellation formulas.
problem Anomaly cancellation formulas for modular forms over Γ^0(2).
method Study and analysis of modular forms over Γ^0(2).
result Anomaly cancellation formulas derived for modular forms over Γ^0(2).
FactorMiner discovers financial alpha factors with low redundancy.
problem Finding novel financial alpha factors in a vast search space.
method Modular Skill Architecture and Experience Memory to distill and guide exploration.
result FactorMiner constructs a diverse library of high-quality factors with competitive performance.
This work argues for the importance of objects in model-based reinforcement learning.
problem Dynamic construction of models in real-world problems.
method Identifies requirements for overcoming limitations in connectionist models.
result Objects are essential for dynamic model construction in reinforcement learning.
Our aim is to introduce and advocate non-Σ (non-symmetric) modular operads. While ordinary modular operads were inspired by the structure of the moduli space of stable complex curves, non-Σ modular operads model surfaces with open strings outputs. An immediate application of our theory is a short proof that the mod…
Neural networks learn modular arithmetic but not all, extending known solutions to generalize.
problem Neural networks struggle with modular arithmetic, especially for polynomials.
method Developed analytical solutions for MLP networks to learn modular addition and multiplication, then combined these solutions to generalize on arbitrary modular polynomials.
result Neural networks can learn and generalize solutions to modular polynomials, supporting the hypothesis that some polynomials are learnable.
Fuchsian groups with a modular embedding have the richest arithmetic properties among non-arithmetic Fuchsian groups. But they are very rare, all known examples being related either to triangle groups or to Teichmueller curves. In Part I of this paper we study the arithmetic properties of the modular embedding and deve…
Modular NNs improve training speed and stability.
problem Complexity in NNs with many parameters or intricate architectures.
method Decompose NN into control and functional modules.
result Modular NNs outperform monolithic ones in training speed and stability.
Improved algorithm for modular links provides upper volume bounds.
problem Understanding the geometry of modular links and Lorenz links.
method Bunch algorithm to study modular links and provide upper volume bounds.
result First upper volume bound independent of word exponents and quadratic in braid index.
Geodesics on modular surface yield arithmetic 3-manifolds.
problem Understanding arithmetic properties of modular surfaces.
method Constructing geodesics and analyzing their lifts.
result Complements of canonical lifts are arithmetic 3-manifolds.
We introduce the notion of the modular class of a Lie algebroid equipped with a Nambu structure. In particular, we recover the modular class of a Nambu-Poisson manifold M with its Nambu tensor Λ as the modular class of the tangent Lie algebroid TM with Nambu structure Λ. We show that many known properties of th…
New modular forms for anomaly cancellation formulas on any dimensional manifolds.
problem Constructing new modular forms for anomaly cancellation formulas.
method Using E8 bundles, constructing modular forms on any dimensional manifolds. result Derived new anomaly cancellation formulas and applications.
Quantum modularity proved for SU(2) TQFT signature on genus 2 surfaces.
problem Proving quantum modularity of SU(2) TQFT signature for genus 2 surfaces.
method Using quantum modularity of generalized Dedekind sums associated with modular forms and trigonometric sum expressions.
result Quantum modularity of SU(2) TQFT signature on genus 2 surfaces proved.
Motivated by a question of Hirzebruch on the possible topological types of cusp cross-sections of Hilbert modular varieties, we give a necessary and sufficient condition for a manifold M to be diffeomorphic to a cusp cross-section of a Hilbert modular variety. Specialized to Hilbert modular surfaces, this proves that e…
Agent learns diverse hierarchical structures in unknown environments.
problem Autonomous discovery and learning of diverse structures in unknown changing environments.
method Progressive construction of a Hierarchy of Observation Latent Models for Exploration Stratification (HOLMES).
result Agent can learn and reuse representations to progressively explore and discover diverse structures.
Countable modular groups found on surfaces with infinite type.
problem Finding modular groups of infinite type surfaces.
method Proving countable modular groups for orientable infinite type surfaces.
result Every orientable infinite type surface has a countable modular group.
Quantum modularity proven for specific theta series.
problem Proving quantum modularity for partial theta series with periodic coefficients.
method Explicit proof using Kontsevich-Zagier series and colored Jones polynomials.
result Kontsevich-Zagier series is a weight 3/2 quantum modular form.
Study Alexander polynomials of modular knots, revealing finite and infinite coefficient properties.
problem Investigate Alexander polynomials of modular knots.
method Use Burau representation and geometric SL2(Z)-invariants. result Alexander polynomials of modular knots have both finite and infinite coefficient properties.
The paper introduces elliptic quasi-modular forms via moduli spaces.
problem Developing a theory of elliptic quasi-modular forms.
method Using moduli spaces and the Gauss-Manin connection.
result Presented a succinct theory of elliptic quasi-modular forms.
In this paper the exact linear relation between the leading eigenvectors of the modularity matrix and the singular vectors of an uncentered data matrix is developed. Based on this analysis the concept of a modularity component is defined, and its properties are developed. It is shown that modularity component analysis …
Sharp lower bounds for modular invariants and Dehn twist coefficients in genus 2 and 3.
problem Finding sharp lower bounds for modular invariants and Dehn twist coefficients.
method Analyzing the relation between fractional Dehn twists and modular invariants, classifying pseudo-periodic maps, and proving rigidity properties.
result Sharp lower bounds for modular invariants and Dehn twist coefficients in genus 2 and 3.