Interactive agent modeling by learning to probe improves understanding of other agents' behaviors.
problem Understanding and predicting the behaviors of other agents in interactive scenarios.
method An interactive agent modeling scheme enabled by encouraging the agent to learn to probe, combining imitation learning and curiosity-driven reinforcement learning.
result The agent model learned by the proposed approach generalizes better and enhances performance in multiple applications.
Estimates interaction laws from agent trajectories without assuming their form.
problem Inferring interaction laws from observational data in complex systems.
method Non-parametric statistical learning approach from trajectory data.
result Effectiveness demonstrated in various disciplines, including physics, opinion dynamics, and biology.
Enactive learning shows agents can learn from their environment, but limited by action choices.
problem Learning and interaction of autonomous agents in complex environments.
method Simulation of artificial agents in maze environments, comparing enactive learning to classical reinforcement learning.
result Enactive agents can learn to avoid unfavorable interactions but performance is limited by action choices.
Modeling and learning turn-taking behaviors in multi-agent systems.
problem Modeling and predicting turn-taking behaviors in dynamic multi-agent systems.
method Individual behavior models (WFSTs) and multi-agent fusion model (logistic regression classifier).
result Accurately models and predicts turn-taking behaviors with high precision.
Randomized feature models learn interaction kernels from agent paths.
problem Learning interaction kernels from noisy agent paths.
method Randomized feature algorithm and sparse regression.
result Pruned features reduce overfitting and lower simulation cost.
Model shows how traders' interactions can create market patterns.
problem Explaining stylized facts in high-frequency trading markets.
method Agent-based model of limit order book trading with zero-intelligence agents.
result Scale-free connectivity between traders reproduces market patterns, while no interaction does not.
MagNet uses neural networks to predict multi-agent dynamics from observations.
problem Predicting the evolution of complex multi-agent systems.
method Formulated a coupled non-linear network with ODE-based state evolution, trained a neural network to discover dynamics from observations.
result Orders of magnitude improvement in prediction accuracy over traditional models.
We consider a financial market model which consists of a financial asset and a large number of interacting agents classified into many types. Different types of agents are heterogeneous in their price expectations. Each agent can change its type based on the current empirical distribution of the types and the equilibri…
MIDAS learns to adaptively control other cars in urban driving scenarios.
problem Autonomous vehicles need to interact with other agents on the road.
method Reinforcement learning with attention mechanism to handle multiple agents.
result MIDAS policies are adaptive and robust to external changes.
New method detects key borrowers in financial networks by considering long-range interactions.
problem Identifying systemically important elements in financial networks.
method Analyzes long-range interactions, considering agent attributes and indirect impacts.
result Identifies two types of key borrowers: major players and intermediaries.
It is known that asset exchange models with symmetric interaction between agents show either a Gibbs/log-normal distribution of assets among the agents or condensation of the entire wealth in the hands of a single agent, depending upon the rules of exchange. Here we explore the effects of introducing asymmetry in the i…
Agent Based Modeling (ABM) has become a widespread approach to model complex interactions. In this chapter after briefly summarizing some features of ABM the different approaches in modeling spatial interactions are discussed. It is stressed that agents can interact either indirectly through a shared environment and/or…
INTAGS uses interactive simulation to improve realism in multi-agent systems.
problem Challenges in developing realistic agent-based simulators for multi-agent systems.
method INTAGS introduces a novel metric to evaluate the difference between real and synthetic multi-agent systems, optimizing a stochastic policy in reinforcement learning to adapt to interactive sequential decision-making environments.
result INTAGS generates more realistic market data compared to state-of-the-art approaches.
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…
We formulate and analyze a multi-agent model for the evolution of individual and systemic risk in which the local agents interact with each other through a central agent who, in turn, is influenced by the mean field of the local agents. The central agent is stabilized by a bistable potential, the only stabilizing force…
TraderTalk uses LLMs to simulate human trading interactions in financial markets.
problem Simulating realistic human trading interactions in financial markets.
method Hybrid ABM with LLM-generated behaviors for detailed conversations.
result Successfully replicates trade-to-order volume ratios in financial markets.
We study consumption behaviour in systems with heterogeneous interacting agents. Two different models are introduced, respectively with long and short range interactions among agents. At any time step an agent decides whether or not to consume a good, doing so if this provides positive utility. Utility is affected by i…
A multi-agent simulator evaluates trading strategies using Market Replay and Interactive Agent-Based Simulation.
problem Evaluate trading strategies using Market Replay and Interactive Agent-Based Simulation.
method Multi-agent simulator for Market Replay and Interactive Agent-Based Simulation.
result IABS provides a more realistic market environment for evaluating trading strategies.
We model a closed economic system with interactions that generates the features of empirical wealth distribution across all wealth brackets, namely a Gibbsian trend in the lower and middle wealth range and a Pareto trend in the higher range, by simply limiting the an agents' interaction to only agents with nearly the s…
Method learns to predict agent interactions from partial observations.
problem Predicting interactions between multiple agents from incomplete data.
method Graph-Structured Variational Recurrent Neural Network (Graph-VRNN) trained end-to-end.
result Graph-VRNN outperforms baselines on sports datasets.
Graph neural network predicts vehicle interactions and trajectories for autonomous driving.
problem Predicting future motion of vehicles in traffic scenes.
method Graph neural network that jointly predicts interaction modes and 5-second future trajectories.
result Jointly predicting trajectories and interaction modes leads to lower trajectory error.
Study explores how wealth dynamics change with preferential interactions in kinetic exchange models.
problem Investigate how preferential interactions affect wealth dynamics and distributions in kinetic exchange models.
method Conducted Monte Carlo simulations to explore two types of preferential interactions: one with random selection and another with wealth difference constraint.
result Emergence of quasi-oligarchic societies and segregation into economic classes observed in preferential interactions.
RFM models predict multi-agent behavior, offering insights and faster learning.
problem Understanding and improving multi-agent systems learning.
method Relational Forward Models (RFM) that learn to predict future agent behavior.
result RFM modules inside agents lead to faster learning compared to baseline methods.
This paper uses a path integral approach to model complex economic systems with many agents.
problem Modeling economic systems with a large number of interacting agents.
method Develops a path integral formalism to describe the behavior of a large number of agents in an economic system.
result The method provides an analytical treatment of business cycle models with many agents, revealing various phases and interactions.
This work develops a learning theory for inferring interaction kernels in complex agent systems.
problem Modeling complex interactions in systems of particles or agents.
method Nonparametric regression and approximation theory.
result Strong consistency and optimal convergence rates for estimators of interaction kernels.
OtoWorld helps agents learn to navigate by listening in interactive environments.
problem Training agents to navigate using auditory information.
method Interactive environment with agents learning to listen and navigate.
result Agents can win at OtoWorld, a navigation game with sound sources.
This paper proposes using variational autoencoders to model opponents in multi-agent systems.
problem Understanding and interacting with opponents in multi-agent systems.
method Variational autoencoders for opponent modeling, with a modification to use local information.
result Our opponent modeling methods achieve equal or greater episodic returns.
Agent learns object segmentation through self-supervised interactions.
problem Object segmentation in visual observations.
method Self-supervised learning through interaction, robust set loss.
result Model generalizes to novel objects and backgrounds.
The paper tackles how weakly interacting agents can learn to escape flat minima in machine learning.
problem Understanding how flat minima affect generalization in machine learning.
method Formalizes the problem as an optimization problem with weakly interacting agents, reviews stochastic processes, and proposes a new algorithm.
result Illustrates the potential of an algorithmic framework for escaping flat minima.
Symmetry-based learning needs interaction with the environment.
problem Defining disentangled representations in dynamic environments.
method Building on Symmetry-Based Disentangled Representation Learning, we argue that agents need to interact with the environment to discover symmetries.
result Agents need to interact with the environment to fully understand symmetries and learn disentangled representations.
New models show agents learn local interactions for collective motion.
problem Understanding how collective motion emerges from individual interactions.
method Developed a new model where agents learn local interaction rules.
result Agents can learn appropriate local interactions without prior assumptions.
Improved PAC guarantees for multi-agent reinforcement learning with noisy communication.
problem Improving exploration in cooperative multi-agent reinforcement learning with communication constraints.
method Develops PAC guarantees for multiple concurrent MDPs with noisy and resource-limited communication.
result Theoretical and empirical improvements in sample complexity for information fusion.
Study optimal investment in large populations of competitive, heterogeneous agents.
problem Maximizing utility in a large, interacting agent system with relative performance concerns.
method Analyzes stochastic utility maximization game in finite and infinite agent settings, using graphon models and backward stochastic differential equations.
result Convergence of Nash equilibria and optimal utilities from finite to infinite agent models under specific conditions.
This essay discusses the advantages of a probabilistic agent-based approach to questions in theoretical economics, from the nature of economic agents, to the nature of the equilibria supported by their interactions. One idea we propose is that "agents" are meta-individual, hierarchically structured objects, that includ…
EpiRL learns to detect gene-gene interactions.
problem Computational challenges in epistasis detection.
method Modeling epistasis as a Markov Decision Process and using reinforcement learning.
result EpiRL discovers highly interacted genes.
Study shows how diverse investors' learning and preferences shape financial markets.
problem Understanding how diverse investor behaviors and preferences affect market dynamics.
method Developed a multi-agent reinforcement learning framework with heterogeneous preferences and learning mechanisms.
result Diverse investors develop differentiated strategies through interaction, leading to realistic market dynamics.
Model for equity trading with asynchronous price updates converging to a stationary return distribution.
problem Equity trading dynamics with asynchronous price updates and varying number of participants.
method Modeling agents' adaptive strategies and using numerical simulations to analyze returns.
result The model converges to a stationary return distribution, with mean returns influenced by adaptive mechanisms and agent interactions.
Agent-based model simulates market dynamics with real-time order matching.
problem Realistic simulation of market dynamics with realistic price impact.
method Agent-based model with asynchronous, event-time order matching.
result Realistic price impact curves and stylized facts presented.
PRECOG predicts future interactions between AVs and other drivers.
problem Autonomous vehicles need to predict human drivers' intentions for safe road behavior.
method Probabilistic forecasting model trained on real and simulated data.
result Our model predicts future interactions more accurately than existing methods.
We introduce a stochastic heterogeneous interacting-agent model for the short-time non-equilibrium evolution of excess demand and price in a stylized asset market. We consider a combination of social interaction within peer groups and individually heterogeneous fundamentalist trading decisions which take into account t…
In this work the system of agents is applied to establish a model of the nonlinear distributed signal processing. The evolution of the system of the agents - by the prediction time scale diversified trend followers, has been studied for the stochastic time-varying environments represented by the real currency-exchange …
Evology models US equity mutual funds interactions for investment strategies.
problem Understanding complex interactions in financial markets.
method Agent-based model (ABM) of US stock market participants and their strategies.
result Trading strategies interact with other market participants and conditions.
Dreamer 4 learns Minecraft tasks from videos alone.
problem Accurately predicting object interactions in complex environments.
method Reinforcement learning inside a fast, accurate world model.
result Dreamer 4 outperforms previous models in Minecraft, learning from only offline data.
Two new exploration methods for multi-agent systems improve team performance.
problem Exploration in transition-dependent multi-agent settings.
method EITI and EDTI, using mutual information and VoI to encourage coordinated exploration.
result Significant improvement in multi-agent performance through coordinated exploration.
Many learning agents impact a financial market model, showing complex dynamics.
problem Understanding the dynamics of financial markets with multiple learning agents.
method Agent-based model of financial market with multiple reinforcement learning agents interacting.
result Inclusion of learning agents changes market dynamics to match empirical data.
Agent learns goals and rewards through language and curiosity.
problem Autonomous agents lack intrinsic motivations and reward functions.
method LE2 algorithm using NL interactions and intrinsic motivations.
result Agent autonomously discovers and grounds goals in real behavior.
New method uncovers global topology through local interactions, reducing algorithm complexity.
problem Global interaction is necessary for forming feature maps that preserve global topology.
method Competing agents engage in local interactions to form feature maps without global interaction.
result Local interactions can uncover global topology, leading to consistent map quality across diverse datasets.
Predicts multiple vehicle trajectories efficiently.
problem Predicting uncertain future motions of agents in dynamic scenes.
method Probabilistic framework learning latent variables for multi-step future modeling.
result State-of-the-art predictions on vehicle trajectory datasets.