Simplified feature selection using a single agent with restructured choice strategy.
problem Efficiency and cost issues in multi-agent reinforced feature selection.
method Single-agent approach with restructured choice strategy, including scanning method, feature prioritization, state representation, and reward scheme.
result Improved efficiency and effectiveness of feature selection.
Regret analysis is challenging in Multi-Agent Reinforcement Learning (MARL) primarily due to the dynamical environments and the decentralized information among agents. We attempt to solve this challenge in the context of decentralized learning in multi-agent linear-quadratic (LQ) dynamical systems. We begin with a simp…
Scaling up model and data size improves imitation learning in single-agent games.
problem Limited recovery of expert behavior in single-agent games using imitation learning.
method Investigate the effect of scaling model and data size on imitation learning performance.
result IL loss and mean return scale with compute budget, resulting in power laws.
Study on multi-agent decision making complexity, showing sample efficiency gaps.
problem Understanding sample efficiency in multi-agent decision making.
method General framework for interactive decision making, focusing on equilibrium computation.
result No 'reasonable' complexity measure can close gaps between single and multiple agents.
Federated learning for combinatorial multi-agent bandits reduces regret and speeds up with fewer communications.
problem Online combinatorial optimization with noisy feedback and cooperation.
method Transforms offline algorithms into online multi-agent algorithms with sublinear regret and communication efficiency.
result Achieves sublinear regret and linear speedup with more agents, communication-efficient.
New RL algorithms reduce costs for single-agent and federated learning.
problem Minimizing costs in RL and federated RL settings.
method Q-EarlySettled-LowCost and FedQ-EarlySettled-LowCost algorithms.
result First algorithms to achieve low burn-in and logarithmic switching costs.
New algorithm reduces regret in multi-agent bandits with malicious agents.
problem Collaboration between honest and malicious agents in multi-armed bandits.
method Dynamic reduction of communication with malicious agents, learning who is malicious.
result Algorithm reduces regret even with a single malicious agent, assuming m is small compared to K. MARLA uses deep reinforcement learning for multi-agent AHT, reducing Bayes risk.
problem Decentralized active hypothesis testing among multiple agents.
method MARLA algorithm using deep multi-agent reinforcement learning.
result MARLA outperforms single-agent learning in AHT problems.
CSAC enables cooperative reinforcement learning for multi-stage tasks.
problem Coordinating consecutive reinforcement learning agents for long-term multi-stage tasks.
method CSAC modifies each agent's policy to maximize both current and next agent's critic.
result CSAC outperforms uncooperative policies and single-agent training in multi-room maze domain.
A multi-agent system improves crypto portfolio management by processing diverse data types.
problem Managing cryptocurrency portfolios requires processing various data types under high volatility.
method A multi-agent system with three specialized agents for market dynamics, news sentiment, and signal fusion.
result The best configuration, Hierarchical (Skill), achieved a 133.52% cumulative return and 1.502 Sharpe ratio.
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.
problem Limited use of AI-agent collaboration in financial research.
method Proposes a multi-agent system for financial investment research.
result Multi-agent system outperforms single-agent models.
RL in MFGs is as hard as solving many single-agent RL problems.
problem Learning Nash Equilibrium in Mean-Field Games (MFGs).
method Introduce P-MBED to measure model complexity, develop a novel exploration strategy, and establish polynomial sample complexity results.
result Learning Nash Equilibrium in MFGs is no more statistically challenging than solving a logarithmic number of single-agent RL problems.
Study on price formation in financial markets with a single default event.
problem Equilibrium price formation in financial markets with a single default risk.
method Characterized optimal strategies using quadratic-growth BSDEs, derived market-clearing condition, and established mean-field BSDE solvability.
result Characterized equilibrium risk premium and its dependence on default risk factors.
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.
problem Designing multi-agent environments for reinforcement learning is challenging.
method Developed intrinsic teacher rewards for multi-agent settings and evaluated them in various tasks.
result Value disagreement was found to be most consistent and effective across tasks.
ARL makes market makers resilient to adversarial conditions.
problem Creating resilient market makers against adversarial attacks.
method Transformed single-agent RL into a zero-sum game between market maker and adversary.
result ARL leads to risk-averse behavior and significant performance improvements.
MRC improves credit assignment in multi-agent LLM systems, achieving high returns and transparency.
problem Lack of principled credit assignment in multi-agent LLM decision systems, vulnerability to regime shifts, and limited transparency.
method Market Regime Council (MRC) computes exact Shapley credits, uses exponentially weighted performance histories, Bayesian adaptive mixture, and regime-dependent multipliers.
result MRC achieves a Sharpe ratio of 1.51 and a cumulative return of 440.1% over 1,037 trading days, ranking first on CR, SR, and IR.
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 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.
problem Extending RL theory to multi-agent settings with large state spaces.
method Proposes an algorithm using an exploiter to find Nash equilibrium policies.
result Proves finding Nash equilibrium is possible with polynomial samples.
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.
problem Multi-agent reinforcement learning with large state spaces and linear function approximations.
method Refined AVLPR framework with data-dependent pessimistic estimation and action-dependent bonuses.
result First algorithm with optimal O(T−1/2) convergence rate and no poly(Amax) dependency. 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.
problem Improving AI cooperation in teams with shared rewards.
method Proposed Partner-Aware strategy extending Upper Confidence Bound for decentralized MAB.
result Achieves logarithmic regret in collaborative decision-making.
New approach tackles non-stationary multi-agent games with black-box methods.
problem Challenges in learning equilibria in non-stationary multi-agent systems.
method Versatile black-box approach applicable to various games, including general-sum, potential, and Markov games.
result Achieves optimal regret bounds for non-stationary games, with or without knowledge of total variation.
One-shot path planning for multiple agents using neural networks.
problem Efficiently generating optimal or near-optimal paths for multiple agents in robotics.
method Utilizes fully convolutional neural networks for one-shot multi-agent path planning.
result Demonstrates successful generation of optimal or near-optimal paths in over 85% of cases for multi-path planning.
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.
problem Risk-sensitive optimal control in LQG systems with major-minor interactions.
method Variational approach, nonlinear necessary and sufficient condition of optimality, equivalent risk-neutral measure, Markovian closed-loop best-response strategies.
result Derives optimal control strategies for LQG risk-sensitive MFGs with major-minor interactions, establishing Nash and ε-Nash equilibria. MA-COPP predicts multi-agent system outcomes using data from a different policy, with probabilistic guarantees.
problem Predicting outcomes in multi-agent systems using data from a different policy.
method Conformal prediction framework applied to multi-agent systems, avoiding exhaustive search.
result Achieves probabilistic guarantees for multi-agent system predictions.
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.
problem Commodity portfolio construction
method Multi-Agent LLM Framework
result LLM strategies outperform Rule Agent in Sharpe terms
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.
problem Decentralized optimization over the Stiefel manifold with private data.
method Gradient tracking with approximate augmented Lagrangian function.
result DESTINY achieves global convergence with a 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.
problem Maximizing total welfare among agents with shared constraints and submodular utilities under bandit feedback.
method Proposes an explore-then-commit strategy with randomized assignments for multi-agent combinatorial bandits.
result Achieves ildeO(T2/3) regret, first for partition-based submodular welfare problem under bandit feedback. Paper tackles RL for power grid topology optimization.
problem Managing large action spaces in growing power networks.
method Hierarchical multi-agent reinforcement learning (MARL) framework.
result MARL framework outperforms single-agent RL methods.
This work improves Q-learning for average-reward MDPs, reducing sample and communication complexities in federated settings.
problem Improving sample complexity of Q-learning for average-reward MDPs.
method Simple Q-learning algorithm with carefully chosen parameters for both single-agent and federated scenarios.
result Established first federated Q-learning algorithm for average-reward MDPs with provable efficiency in sample and communication complexities.
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.
problem How to encourage cooperation among RL agents in a shared environment.
method Each agent learns a reward function to influence others, optimizing for its own and others' extrinsic objectives.
result Agents significantly outperform standard RL in Markov games, often finding near-optimal division of labor.
Algorithm maximizes total reward in multi-agent bandits with adversarial corruptions.
problem Maximizing total reward in multi-agent bandits with adversarial corruptions.
method Proposes a cooperative learning algorithm robust to adversarial corruptions.
result Demonstrates an additive O((L/Lmin)C) regret term for an adversary with unknown corruption budget. 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.
problem Modeling preferences based on multiple, often competing objectives.
method Modeling priorities lexicographically and inferring multi-objective rewards from observed preferences.
result Lexicographically-ordered rewards provide a better understanding of preferences and improve policies.