arxiv_cv
Abstract: Abstract: The capability of a novel Kullback-Leibler divergence method is examined
herein within the Kalman filter framework to select the input-parameter-state
estimation execution with the most plausible results. This identification
suffers from th...
#Control Theory#State Estimation#Machine Learning#Information Theory#System Identification
arxiv_cl
Abstract: Abstract: The trajectory of AI development suggests that we will increasingly rely on
agent-based systems composed of independently developed agents with different
information, privileges, and tools. The success of these systems will
critically depen...
#Multi-Agent Systems#AI Collaboration#Reinforcement Learning#Agent Coordination#Benchmarking
arxiv_cl
Abstract: Abstract: As LLM-based agents become increasingly autonomous and will more freely
interact with each other, studying the interplay among them becomes crucial to
anticipate emergent phenomena and potential risks. In this work, we provide an
in-depth a...
#AI Safety#Multi-Agent Systems#Human-AI Interaction#AI Ethics#Large Language Models
arxiv_ml
Abstract: Abstract: AI research agents are demonstrating great potential to accelerate scientific
progress by automating the design, implementation, and training of machine
learning models. We focus on methods for improving agents' performance on
MLE-bench, a ...
#Automated Machine Learning (AutoML)#AI Agents#Search Algorithms#Reinforcement Learning#Machine Learning Benchmarking
arxiv_ml
Abstract: Abstract: One of the main challenges in managing traffic at multilane intersections is
ensuring smooth coordination between human-driven vehicles (HDVs) and connected
autonomous vehicles (CAVs). This paper presents a novel traffic signal control
fram...
#Intelligent Transportation Systems#Reinforcement Learning#Graph Neural Networks#Autonomous Driving#Traffic Management
arxiv_ml
Abstract: Abstract: Practitioners designing reinforcement learning policies face a fundamental
challenge: translating intended behavioral objectives into representative
reward functions. This challenge stems from behavioral intent requiring
simultaneous achiev...
#Multi-Objective Reinforcement Learning#Reward Engineering#Robotics Control#AI Alignment#Decision Making Under Uncertainty
arxiv_ml
Abstract: Abstract: No-regret learning dynamics play a central role in game theory, enabling
decentralized convergence to equilibrium for concepts such as Coarse Correlated
Equilibrium (CCE) or Correlated Equilibrium (CE). In this work, we improve the
converge...
#Game Theory#Multi-Agent Reinforcement Learning#Online Learning#Convergence Analysis#Algorithmic Game Theory
arxiv_ml
Abstract: Abstract: In Major League Baseball, strategy and planning are major factors in
determining the outcome of a game. Previous studies have aided this by building
machine learning models for predicting the winning team of any given game. We
extend this w...
#Sports Analytics#Machine Learning#Predictive Modeling#Statistical Analysis#Behavioral Economics
arxiv_ml
Abstract: Abstract: Goal-Conditioned Reinforcement Learning (GCRL) enables agents to autonomously
acquire diverse behaviors, but faces major challenges in visual environments
due to high-dimensional, semantically sparse observations. In the online
setting, whe...
#Reinforcement Learning#Representation Learning#Exploration Strategies#Goal-Conditioned Learning#Online Learning
arxiv_ml
Abstract: Abstract: Bayesian optimization is highly effective for optimizing
expensive-to-evaluate black-box functions, but it faces significant
computational challenges due to the high computational complexity of Gaussian
processes, which results in a total t...
#Optimization#Machine Learning#Bayesian Methods#Algorithm Design
arxiv_ml
Abstract: Abstract: We develop new accelerated first-order algorithms in the Frank-Wolfe (FW)
family for minimizing smooth convex functions over compact convex sets, with a
focus on two prominent constraint classes: (1) polytopes and (2) matrix domains
given b...
#Optimization Algorithms#Convex Optimization#Machine Learning Theory#Algorithm Design#Sparse Optimization
arxiv_ml
Abstract: Abstract: We argue that the negative transfer problem occurring when the new task to
learn arrives is an important problem that needs not be overlooked when
developing effective Continual Reinforcement Learning (CRL) algorithms. Through
comprehensive...
#Reinforcement Learning#Continual Learning#Machine Learning#Robotics#Artificial Intelligence
arxiv_ml
Abstract: Abstract: Conventional Multi-Armed Bandit (MAB) algorithms are designed for stationary
environments, where the reward distributions associated with the arms do not
change with time. In many applications, however, the environment is more
accurately mo...
#Reinforcement Learning#Online Learning#Change Detection#Algorithm Analysis
arxiv_ml
Abstract: Abstract: We study a two-player zero-sum game in which the row player aims to maximize
their payoff against an adversarial column player, under an unknown payoff
matrix estimated through bandit feedback. We propose three algorithms based on
the Explo...
#Game Theory#Online Learning#Reinforcement Learning#Algorithmic Game Theory#Decision Theory
arxiv_ml
Abstract: Abstract: Offline goal-conditioned reinforcement learning (GCRL) offers a practical
learning paradigm in which goal-reaching policies are trained from abundant
state-action trajectory datasets without additional environment interaction.
However, offl...
#Offline Reinforcement Learning#Hierarchical Reinforcement Learning#Goal-Conditioned Reinforcement Learning#Long-Horizon Planning#Value Function Approximation
arxiv_ml
Abstract: Abstract: Offline preference-based reinforcement learning (PbRL) provides an effective
way to overcome the challenges of designing reward and the high costs of online
interaction. However, since labeling preference needs real-time human feedback,
acq...
#Offline Reinforcement Learning#Preference Learning#Sample Efficiency#Reward Modeling#Human-in-the-Loop Learning
arxiv_ml
Abstract: Abstract: Continuous control of non-stationary environments is a major challenge for
deep reinforcement learning algorithms. The time-dependency of the state
transition dynamics aggravates the notorious stability problems of model-free
deep actor-cri...
#Reinforcement Learning#Non-Stationary Environments#Control Theory#Uncertainty Quantification#Exploration Strategies
arxiv_ml
Abstract: Abstract: This paper proposes a reinforcement learning (RL)-aided cognitive framework
for massive MIMO-based integrated sensing and communication (ISAC) systems
employing a uniform planar array (UPA). The focus is on enhancing radar sensing
performan...
#Integrated Sensing and Communication (ISAC)#Reinforcement Learning in Communications#Cognitive Radio#Signal Processing#Wireless Systems Optimization
arxiv_ml
Abstract: Abstract: We study the problem of learning multi-task, multi-agent policies for
cooperative, temporal objectives, under centralized training, decentralized
execution. In this setting, using automata to represent tasks enables the
decomposition of com...
#Multi-Agent Systems#Reinforcement Learning#Cooperative AI#Task Planning#Decentralized Control
arxiv_ml
Abstract: Abstract: This paper studies the high-dimensional scaling limits of online stochastic
gradient descent (SGD) for single-layer networks. Building on the seminal work
of Saad and Solla, which analyzed the deterministic (ballistic) scaling limits
of SGD...
#Machine Learning Theory#Optimization Algorithms#Deep Learning Analysis#Statistical Mechanics#Stochastic Processes
arxiv_ml
Abstract: Abstract: This paper presents a novel approach to many-vs-many missile guidance using
virtual targets (VTs) generated by a Normalizing Flows-based trajectory
predictor. Rather than assigning n interceptors directly to m physical targets
through conve...
#Guidance, Navigation, and Control (GNC)#Operations Research#Machine Learning#Defense Technology#Multi-Agent Systems
arxiv_ml
Abstract: Abstract: Smoothness is known to be crucial for acceleration in offline optimization,
and for gradient-variation regret minimization in online learning.
Interestingly, these two problems are actually closely connected -- accelerated
optimization can ...
#Online Learning Theory#Optimization Algorithms#Regret Minimization#Adaptive Methods#Convex Analysis
arxiv_ai
Abstract: Abstract: This paper tackles the critical challenge of human-AI complementarity in
decision-making. Departing from the traditional focus on algorithmic
performance in favor of performance of the human-AI team, and moving past the
framing of collabora...
#Human-AI Team Complementarity#Learning Policies for Collaborative Decision-Making#Robustness to Model Misspecifications#Exploiting Divergent Human and AI Behaviors
arxiv_ai
Abstract: Abstract: The openness of social media enables the free exchange of opinions, but it
also presents challenges in guiding opinion evolution towards global consensus.
Existing methods often directly modify user views or enforce cross-group
connections....
#Multi-Agent Systems#Opinion Dynamics#Social Network Analysis#Reinforcement Learning#Consensus Building
arxiv_ml
Abstract: Abstract: Agents that understand objects and their interactions can learn policies that
are more robust and transferable. However, most object-centric RL methods
factor state by individual objects while leaving interactions implicit. We
introduce the...
#Reinforcement Learning#World Models#Object-Centric Representation#Robotics#Generalization
arxiv_ml
Abstract: Abstract: We present a novel decentralized algorithm for coverage control in unknown
spatial environments modeled by Gaussian Processes (GPs). To trade-off between
exploration and exploitation, each agent autonomously determines its trajectory
by min...
#Decentralized Control#Robotics#Spatial Coverage#Gaussian Processes#Multi-Agent Systems
arxiv_ml
Abstract: Abstract: Training a team of agents from scratch in multi-agent reinforcement learning
(MARL) is highly inefficient, much like asking beginners to play a symphony
together without first practicing solo. Existing methods, such as offline or
transferab...
#Multi-Agent Systems#Reinforcement Learning#Transfer Learning#Cooperative AI#Machine Learning Efficiency
arxiv_ml
Abstract: Abstract: Mixed-Integer Linear Programming (MILP) is a fundamental and powerful
framework for modeling complex optimization problems across diverse domains.
Recently, learning-based methods have shown great promise in accelerating MILP
solvers by pre...
#Optimization#Machine Learning for Operations Research#Domain Adaptation#Mixture-of-Experts#Robustness
arxiv_ml
Abstract: Abstract: The capacitated location-routing problems (CLRPs) are classical problems in
combinatorial optimization, which require simultaneously making location and
routing decisions. In CLRPs, the complex constraints and the intricate
relationships be...
#Combinatorial Optimization#Deep Reinforcement Learning#Operations Research#Logistics and Supply Chain Management#AI for Optimization
arxiv_ai
Abstract: Abstract: Deep reinforcement learning (RL) agents rely on shortcut learning, preventing
them from generalizing to slightly different environments. To address this
problem, symbolic method, that use object-centric states, have been developed.
However,...
#Interpretable AI#Reinforcement Learning#Neurosymbolic AI#Generalization in RL#Representation Learning