arXiv research

Simplified feature selection using a single agent with restructured choice strategy.

Scaling up model and data size improves imitation learning in single-agent games.

New algorithm reduces learning regret in multi-agent systems with unknown dynamics.

Study on multi-agent decision making complexity, showing sample efficiency gaps.

Federated learning for combinatorial multi-agent bandits reduces regret and speeds up with fewer communications.

New RL algorithms reduce costs for single-agent and federated learning.

New algorithm reduces regret in multi-agent bandits with malicious agents.

MARLA uses deep reinforcement learning for multi-agent AHT, reducing Bayes risk.

CSAC enables cooperative reinforcement learning for multi-stage tasks.

A multi-agent system improves crypto portfolio management by processing diverse data types.

A variety of cooperative multi-agent control problems require agents to achieve individual goals while contributing to collective success. This multi-goal multi-agent setting poses difficulties for recent algorithms, which primarily target settings with a single global reward, due to two new challenges: efficient explo…

A dynamic agent model is introduced with an annual random wealth multiplicative process followed by taxes paid according to a linear wealth-dependent tax rate. If poor agents pay higher tax rates than rich agents, eventually all wealth becomes concentrated in the hands of a single agent. By contrast, if poor agents are…

Modeling the purposeful behavior of imperfect agents from a small number of observations is a challenging task. When restricted to the single-agent decision-theoretic setting, inverse optimal control techniques assume that observed behavior is an approximately optimal solution to an unknown decision problem. These tech…

We aim to jointly optimize antenna tilt angle, and vertical and horizontal half-power beamwidths of the macrocells in a heterogeneous cellular network (HetNet). The interactions between the cells, most notably due to their coupled interference render this optimization prohibitively complex. Utilizing a single agent rei…

Enhances financial analysis with multi-agent collaboration.

RL in MFGs is as hard as solving many single-agent RL problems.

Study on price formation in financial markets with a single default event.

Increasing energy efficiency in buildings can reduce costs and emissions substantially. Historically, this has been treated as a local, or single-agent, optimization problem. However, many buildings utilize the same types of thermal equipment e.g. electric heaters and hot water vessels. During operation, occupants in t…

Agents that can learn to imitate given video observation -- \emph{without direct access to state or action information} are more applicable to learning in the natural world. However, formulating a reinforcement learning (RL) agent that facilitates this goal remains a significant challenge. We approach this challenge us…

AutoDIME automates design of multi-agent environments for RL.

ARL makes market makers resilient to adversarial conditions.

MRC improves credit assignment in multi-agent LLM systems, achieving high returns and transparency.

Unified policy controls diverse agents through modular neural networks.

This paper extends off-policy reinforcement learning to the multi-agent case in which a set of networked agents communicating with their neighbors according to a time-varying graph collaboratively evaluates and improves a target policy while following a distinct behavior policy. To this end, the paper develops a multi-…

New algorithm finds Nash equilibrium in multi-agent games.

In this paper, we present a method for learning from video demonstrations by using human feedback to construct a mapping between the standard representation of the agent and the visual representation of the demonstration. In this way, we leverage the advantages of both these representations, i.e., we learn the policy u…

In this paper, we explore using deep reinforcement learning for problems with multiple agents. Most existing methods for deep multi-agent reinforcement learning consider only a small number of agents. When the number of agents increases, the dimensionality of the input and control spaces increase as well, and these met…

New algorithm tackles multi-agent reinforcement learning with optimal convergence rate.

Reinforcement learning in multi-agent scenarios is important for real-world applications but presents challenges beyond those seen in single-agent settings. We present an actor-critic algorithm that trains decentralized policies in multi-agent settings, using centrally computed critics that share an attention mechanism…

Partner-aware algorithms improve AI collaboration in multi-agent settings.

New approach tackles non-stationary multi-agent games with black-box methods.

One-shot path planning for multiple agents using neural networks.

We present a linear agent based model on brand competition. Each agent belongs to one of the two brands and interacts with its nearest neighbors. In the process the agent can decide to change to the other brand if the move is beneficial. The numerical simulations show that the systems always condenses into a state when…

Develops variational framework for LQG risk-sensitive MFGs with major-minor interactions.

MA-COPP predicts multi-agent system outcomes using data from a different policy, with probabilistic guarantees.

Reproducibility in reinforcement learning is challenging: uncontrolled stochasticity from many sources, such as the learning algorithm, the learned policy, and the environment itself have led researchers to report the performance of learned agents using aggregate metrics of performance over multiple random seeds for a …

LLMs add value in commodity portfolio construction when information set and implementation rules are held fixed.

Sample efficiency and scalability to a large number of agents are two important goals for multi-agent reinforcement learning systems. Recent works got us closer to those goals, addressing non-stationarity of the environment from a single agent's perspective by utilizing a deep net critic which depends on all observatio…

A new decentralized algorithm DESTINY solves optimization over Stiefel manifold with single communication round.

Many real world tasks require multiple agents to work together. Multi-agent reinforcement learning (RL) methods have been proposed in recent years to solve these tasks, but current methods often fail to efficiently learn policies. We thus investigate the presence of a common weakness in single-agent RL, namely value fu…

New framework tackles submodular welfare with multi-agent combinatorial bandits.

Paper tackles RL for power grid topology optimization.

This work improves Q-learning for average-reward MDPs, reducing sample and communication complexities in federated settings.

This paper analyzes a class of infinite-time-horizon stochastic games with singular controls motivated from the partially reversible problem. It provides an explicit solution for the mean-field game (MFG) and presents sensitivity analysis to compare the solution for the MFG with that for the single-agent control proble…

Agents learn to give rewards to others in a shared learning environment.

Algorithm maximizes total reward in multi-agent bandits with adversarial corruptions.

We propose a method for modeling and learning turn-taking behaviors for accessing a shared resource. We model the individual behavior for each agent in an interaction and then use a multi-agent fusion model to generate a summary over the expected actions of the group to render the model independent of the number of age…

The paper proposes a method to infer multi-objective rewards from preferences.