Study optimal contracts for Principals hiring a common Agent in continuous time.
problem Optimal contracts for Principals hiring a common Agent in a continuous time setting.
method Reduction of optimisation problem to coupled HJB equations, analysis of specific linear-quadratic model.
result Optimal effort and remunerations coincide only in the first best case.
Framework for robust control in cooperative systems with uncertain common noise.
problem Optimizing collective behavior of agents in the presence of uncertain common noise.
method Proposes a robust mean-field control framework and proves existence of optimal controls.
result Existence of optimal open-loop controls linked to a lifted robust Markov decision problem.
Deep RL agents vary significantly in Atari environments.
problem Challenges in reproducibility due to stochasticity.
method Experiments with OpenAI Baselines agents.
result Variability in agent performance is significant and underreported.
The study shows how probability weighting can lead to betting in a risk-averse economy.
problem Understanding how probability weighting affects economic behavior and risk aversion.
method Examining a von Neumann-Morgenstern economy with an RDU agent to model probability weighting effects.
result Probability weighting can lead to endogenous betting in an economy with common beliefs.
Study optimizes interbank lending and borrowing to reduce systemic risk.
problem Optimizing lending and borrowing in interbank markets to mitigate systemic risk.
method Risk-sensitive mean field games with common noise, convex analysis, Fokker-Planck equations, first hitting time method.
result Risk-averse behavior reduces individual and systemic bank risks.
The paper studies risk-sharing allocations for risk-seeking agents using a common distortion risk measure.
problem Characterizing Pareto-optimal risk-sharing allocations for risk-seeking agents.
method Modeling preferences with a common distortion risk measure and analyzing three settings: risk-averse, risk-seeking, and inverse S-shaped distortion.
result Pareto-optimal allocations for risk-seeking agents are counter-monotonic, not comonotonic.
Algorithm for decentralized competition among adaptive agents.
problem Decentralized competition among adaptive networks.
method Developed an algorithm for decentralized competition among teams of adaptive agents.
result Algorithm enables decentralized competition among adaptive agents.
REFIL learns from imagined sub-group interactions to improve multi-agent reinforcement learning.
problem Learning efficiency in multi-agent reinforcement learning settings.
method Randomized Entity-wise Factorization (REFIL) approach.
result REFIL outperforms all strong baselines in challenging multi-task StarCraft settings.
Explains financial market simulation mechanisms and agent behaviors.
problem Necessity of including fundamental value in multiagent financial market simulations.
method Discusses three methods for generating fundamental value and illustrates one Bayesian agent's estimation process.
result Presentation of two widely examined agents: Zero Intelligence and Heuristic Belief Learning.
Game theory models how agents trade in a risky asset considering price impact and a common signal.
problem Modeling how financial agents liquidate assets in a risky market with price impact and a common signal.
method Formulated and solved a multi-player stochastic differential game and mean field game.
result Equilibrium strategies reveal how agents adjust the predictive trading signal to price impact.
Study analyzes investment strategies for fund managers competing in a common market.
problem Optimal investment strategies for fund managers competing in a common market with relative performance criteria.
method Construct explicit constant equilibrium strategies for both finite population games and mean field games.
result Explicit strategies show how competition affects investment behavior in risky assets.
Market equilibrium price proven in a large-agent model.
problem Proving market equilibrium in a large-agent setting.
method Proved existence of equilibrium price in a complete, continuous time market with infinite agents.
result The equilibrium price dynamics decouple as the number of agents increases.
New approach for multitask learning over networks sharing a common latent feature.
problem Learning multiple tasks simultaneously in a distributed network.
method Assumes shared latent feature representation; develops distributed online algorithms.
result Unified framework for analyzing mean-square-error performance.
Solves rank-dependent mean field game with common noise.
problem Rank-dependent rewards in competitive game settings.
method Mean field game approach with common noise.
result Approximate Nash equilibrium and convergence rate.
Reduces overestimation bias in multi-agent RL, improving performance.
problem Value function overestimation bias in multi-agent RL.
method Double centralized critics to reduce overestimation bias.
result Significant improvement in performance on mixed tasks.
Survey examines LLMs in financial trading.
problem Using LLMs to outperform professional traders in finance.
method Comprehensive review of current research on LLMs in financial trading.
result LLMs can potentially outperform professional traders in backtesting.
A game where agents solve optimal stopping problems interactively.
problem Optimal stopping problems in a mean field game setting.
method Formulated a mean field stochastic game, solved with a continuum of agents, and identified equilibria through a simple equation.
result Equilibria identified and the dynamics in the population analyzed.
We propose a set of conservative models in which agents exchange wealth with a preference in the choice of interacting agents in different ways. The common feature in all the models is that the temporary values of financial status of agents is a deciding factor for interaction. Other factors which may play important ro…
Study competitive agents' optimal consumption and investment strategies with relative performance criteria.
problem Optimizing consumption and investment strategies for multiple agents with relative performance considerations.
method Derived a closed-form solution for an n-player game and mean field game, analyzing the impact of risk tolerance and competitiveness parameters. result Unique equilibria found, showing nonlinear and non-monotone dependence on agents' risk tolerance and competitiveness parameters.
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.
Study on optimal bubble riding with price-dependent entry times in a mean field game model.
problem Optimal bubble riding with price-dependent entry times.
method Mean field game of controls with common noise and random entry time, existence result obtained through discretization and limit analysis.
result Existence of equilibrium in the mean field game model.
Proposes Nash averaging to improve evaluation in machine learning.
problem Overwhelming choices in evaluation suites and attacks have diluted the basic model.
method Detailed analysis of evaluation scenarios leads to Nash averaging, which adapts to data redundancies.
result Nash averaging encourages maximally inclusive evaluation, reducing bias.
We show that there is a common mode of origin for the power laws observed in two different models: (i) the Pareto law for the distribution of money among the agents with random saving propensities in an ideal gas-like market model and (ii) the Gutenberg-Richter law for the distribution of overlaps in a fractal-overlap …
Review of recent advances in decentralized MARL with networked agents.
problem Sequential decision-making by networked agents without central coordination.
method Analysis of recent algorithms and their theoretical foundations.
result Inspiring more research in this challenging area.
Study optimal investment and consumption strategies for competitive agents with habit formation.
problem Optimal investment and consumption strategies for competitive agents with habit formation.
method Formulated n-agent game problems and mean field game problems, derived mean field equilibrium, constructed approximate Nash equilibrium.
result Explicit convergence order of approximate Nash equilibrium can be obtained.
The paper analyzes strategic behavior in reinsurance transactions leading to Nash equilibria.
problem Strategic behavior in reinsurance transactions affecting risk aversion and welfare gains.
method Identifying Nash equilibria within a class of risk measures.
result At strictly beneficial Nash equilibria, agents appear homogeneous in risk preferences.
Efficiently explores concurrent RL agents for practical scale problems.
problem Efficiently exploring multiple RL agents in a shared environment.
method Combines seed sampling and randomized value function learning.
result Approach is competitive and learns quickly with fewer agents.
New algorithms tackle multi-agent problems with hybrid action spaces.
problem Applying deep reinforcement learning to multi-agent problems with discrete-continuous hybrid action spaces.
method Proposed two novel algorithms: Deep MAPQN and Deep MAHHQN, using centralized training and decentralized execution.
result Empirical results show both algorithms significantly outperform existing methods.
Proposes a model for multi-agent reinforcement learning with hierarchical graph attention network.
problem Limited transferability of trained policies to new multi-agent tasks.
method Uses hierarchical graph attention network for representation learning and multi-agent actor-critic for policy learning.
result Demonstrates superior performance in mixed cooperative and competitive tasks compared to existing methods.
Adaptive policies for multi-agent RL improve adaptiveness in changing environments.
problem Non-stationarity in multi-agent reinforcement learning where other agents may alter their policies.
method Train multiple adaptive policies for each agent and a policy predictor to select the best policy at execution time.
result Agents trained with our method outperform state-of-the-art methods in all tested environments.
Researchers develop multi-agent systems for quadcopters to collaborate in missions.
problem Enable multiple quadcopters to work together in remote sensing tasks.
method Agent dynamics, network topologies, collective behaviors, agreement protocol, equations of motion for quadcopters.
result Multi-agent systems can successfully collaborate in remote sensing missions.
A new algorithm reduces regret in cooperative multi-agent bandits with heavy-tailed data.
problem Cooperative multi-agent bandits with heavy-tailed data.
method MP-UCB algorithm incorporating robust estimation with message-passing protocol.
result Optimal regret bounds for MP-UCB in various settings.
Analyze nonlinear filtering in distributed networks, focusing on multitask scenarios.
problem Model estimation in distributed environments with streaming measurements and local computations.
method Kernel-based algorithm for multitask nonlinear system modeling.
result The proposed algorithm can converge to different models for each agent in multitask scenarios.
AEC Games model represents software MARL environments better than POSGs.
problem POSGs are conceptually unsuitable for software MARL environments.
method Introduced AEC Games model as an equivalent to POSGs.
result AEC Games model is more representative of software MARL environments.
DASA speeds up SA with delayed agents, achieving N-fold speedup.
problem Speeding up Stochastic Approximation with asynchronous delays.
method DASA: Delay-Adaptive Multi-Agent Stochastic Approximation algorithm.
result First algorithm with convergence rate dependent on mixing time and average delay.
Distributed processing over networks relies on in-network processing and cooperation among neighboring agents. Cooperation is beneficial when agents share a common objective. However, in many applications agents may belong to different clusters that pursue different objectives. Then, indiscriminate cooperation will lea…
Paper develops a private algorithm for multi-agent learning in bandits.
problem Private cooperative learning in decentralized systems.
method Developed extsc{FedUCB} algorithm for multi-agent learning.
result Improves pseudoregret bounds and empirical performance.
New framework for multi-agent reinforcement learning improves coordination and efficiency.
problem Coordination and effective learning in complex multi-agent systems.
method Centralized training and decentralized execution via policy distillation.
result Significantly better performance and higher sample efficiency.
Study many-player investment-consumption games with power FPPs, finding market-risk preference affects consumption.
problem Investment and consumption optimization in a mean field competition setting.
method Solve many-player and mean field games using power FPPs, providing closed-form solutions.
result Market-risk relative consumption preference affects agent's consumption decisions.
A fully decentralized multi-agent algorithm converges linearly with minimal memory.
problem Efficiently evaluating policies in multi-agent settings with limited exploration.
method Fully decentralized, combining off-policy learning, eligibility traces, and linear function approximation.
result Achieves linear convergence with minimal memory requirements.
Agents minimize individual regret in a networked multi-armed bandit problem.
problem Minimizing individual regret in a networked multi-armed bandit problem.
method Regret minimization algorithms for agents communicating over a network.
result Guaranteed individual expected regret of $\widetilde{O}\left(\sqrt{\left(1+\frac{K}{\left|\mathcal{N}\left(v
ight)
ight|}
ight)T}
ight)$ for each agent.
Paper tackles resilient control for multi-agent systems under attack.
problem Synchronization of output passive agents under Byzantine attacks.
method Distributed event-triggered control framework, decentralized detection, learning-based estimation and mitigation.
result Learning-based control mitigates adversarial attacks on synchronization.
New modeling approach for self-organizing complex systems.
problem Identifying general principles of self-organizing complex systems.
method Self-deploying system structure and activities for goal-driven agents.
result Self-organization emerges from rational activity algorithm based on goals dependency network.
Enhances anomaly detection in financial markets using AI agents.
problem Manual verification of financial market anomalies is time-consuming and error-prone.
method A multi-agent LLM framework for automated anomaly detection.
result Framework reduces human intervention and improves efficiency and accuracy.
New communication topologies improve deep reinforcement learning performance.
problem Improving performance of learning agents in distributed reinforcement learning.
method Examined four graph families for communication topologies and found Erdos-Renyi random graphs to outperform fully connected topologies.
result Erdos-Renyi random graphs can improve performance of distributed learning agents.
Paper studies IPG method's robustness in noisy distributed linear regression.
problem Distributed linear regression with noise.
method Iteratively Pre-conditioned Gradient-descent (IPG) method.
result IPG method's robustness against noise compared favorably to state-of-the-art algorithms.
M3RL trains a manager to infer worker minds and assign tasks for optimal collaboration.
problem Optimal coordination among self-interested agents with diverse preferences and skills.
method Mind-aware Multi-agent Management Reinforcement Learning (M^3RL) that infers worker minds and assigns tasks.
result Effective in modeling worker minds and achieving optimal ad-hoc teaming.
Proposes a graph neural network for efficient multi-agent routing.
problem Routing multiple agents in complex, sparsely connected graphs with dynamic traffic.
method Value Iteration Network based on graph neural networks for online coordination.
result Significantly outperforms traditional methods in terms of cost and runtime.