Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

295786114 · Jun 202019922001200920172026
48 results for agent incentives

This paper addresses reward estimation and incentive design for agents with hidden rewards.

problem Estimating and incentivizing agents with unknown rewards in a learning setting.
method Repeated adverse selection game with a self-interested learning agent and a learning principal. Introduces an estimator for consistent reward estimation and a data-driven incentive policy.
result Finite-sample consistency of the estimator and a rigorous regret bound for the principal.

The paper develops an economic foundation for multi-agent learning in markets.

problem Learning dynamics in markets with strategic externalities.
method A two-phase incentive mechanism that estimates and uses implementable transfers to steer long-run dynamics.
result The mechanism achieves sublinear social-welfare regret and asymptotically optimal welfare under mild rationality and exploration conditions.

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.

COBRA addresses strategic behavior in online platforms by ensuring truthful reporting without monetary incentives.

problem Ensuring truthful reporting from strategic agents in online platforms.
method Proposes COBRA, an algorithm for contextual bandits involving strategic agents that disincentivizes strategic behavior.
result COBRA achieves sub-linear regret guarantee and incentive compatibility without monetary incentives.

No-regret learning with strategic experts, incentivized.

problem Online learning with strategic experts who misreport beliefs.
method Building on wagering mechanisms, we provide algorithms for no-regret and incentive compatibility in both full and partial information settings.
result Our algorithms achieve no regret and incentive compatibility for myopic experts, with comparable regret to classic no-regret algorithms and diminishing regret for forward-looking agents.

Study allocates resources to strategic agents while balancing cost and incentives.

problem Dynamic allocation of reusable resources to strategic agents with private valuations under long-term cost constraints.
method Incentive-aware framework combining epoch-based lazy updates and randomized exploration rounds.
result Achieves ildeO(T) ilde{\mathcal{O}}(\sqrt{T}) social welfare regret, satisfies all cost constraints, and ensures incentive alignment.

Study designs steering rewards for MFGs with unknown dynamics and model uncertainty.

problem Designing incentives for large populations of agents in MFGs with uncertain model details.
method Developed optimistic exploration algorithms for agents with no-adaptive regret behaviors.
result Sub-linear regret guarantees for cumulative gaps between agent behaviors and desired outcomes.

Study designs incentives for adapting multi-agent systems without knowing their learning dynamics.

problem Designing incentives for an adapting population in multi-agent systems without prior knowledge of their learning dynamics.
method Introduces a model-based non-episodic Reinforcement Learning (RL) formulation for steering Markovian agents towards desired policies, focusing on history-dependent strategies to handle model uncertainty.
result Identifies conditions for the existence of steering strategies to guide agents to desired policies and provides empirical algorithms to approximately solve the objective.

How can we design safe reinforcement learning agents that avoid unnecessary disruptions to their environment? We show that current approaches to penalizing side effects can introduce bad incentives, e.g. to prevent any irreversible changes in the environment, including the actions of other agents. To isolate the source…

2018-06-04abs ↗pdf ↗

Forward hedging reshapes incentive provision in firms.

problem How does forward hedging affect incentive provision in firms?
method We consider a CARA framework to jointly characterize optimal production, compensation, and static hedging in equilibrium.
result Delegation and external hedging are partial substitutes, and delegation can increase firm value even when the agent is more risk averse.

A study on how a principal can incentivize an agent to make better decisions in a repeated game.

problem Optimizing a principal's utility in a misaligned principal-agent bandit game.
method Developed nearly optimal learning algorithms for the principal's regret in multi-armed and linear contextual settings.
result The principal can iteratively learn an incentive policy to maximize her total utility.

We study how information perturbations can destabilize two-sided matching markets. In our model, agents arrive on the market over two periods, while agents in the first period do not know the types of those arriving later. Agents already present in the market may match early or wait for the small group of new entrants.…

2010-09-03abs ↗pdf ↗

Insurance contracts for autonomous AI agents must be actuarially sound and resistant to gaming.

problem Designing insurance contracts for autonomous AI agents that are actuarially sound and resistant to gaming.
method Characterizing a five-attack space and proving the actuarial runtime is gaming-resistant.
result An incentive-compatible layer for actuarial control of autonomous-agent side effects.

Study incentive efficiency in monopoly insurance markets with hidden information.

problem Maximizing social welfare in a monopoly insurance market with hidden agent types.
method Maximizes social welfare function subject to incentive compatibility and individual rationality constraints.
result Optimal menus of contracts depend on the level of social welfare weight and agent risk attitudes.

Study of repeated games with unobserved agent rewards using MAB framework.

problem Designing policies for principals in repeated principal-agent games with unobservable agent rewards.
method Developed a policy achieving low regret (square-root regret up to a log factor) for perfect-knowledge agents.
result Constructed an estimator for agent's expected reward and designed a policy achieving low regret.

This study examines how DMMs affect market liquidity and competition.

problem The impact of DMMs on market liquidity and competition.
method Agent-based simulations to explore the effects of varying competition levels and incentive structures among DMMs.
result Optimal competition among DMMs maximizes liquidity benefits without negatively impacting price discovery.

New approach incentivizes strategic agents to explore, making exploration almost free.

problem Incentivized exploration in multi-armed bandits with long-term strategic agents.
method Simple incentive-provision strategy, best arm identification algorithm, and UCB lower bound.
result Exploration can be (almost) free when there are many learning agents.

We study a game-theoretic variant of the maximum circulation problem. In a flow allocation game, we are given a directed flow network. Each node is a rational agent and can strategically allocate any incoming flow to the outgoing edges. Given the strategy choices of all agents, a maximal circulation that adheres to the…

2019-08-05abs ↗pdf ↗

Study of repeated principal-agent bandit game with self-interested and exploratory learning agents.

problem Interaction between principal and agent in unknown environments with learning and exploration behaviors.
method Developed algorithms for self-interested and exploratory learning agents with bandit feedback, achieving regret bounds.
result Achieved O~(T2/3)\widetilde{O}(T^{2/3}) regret bound for exploratory learning agent in i.i.d. reward setup.

Heterogeneous SVO leads to diverse policies in sequential social dilemmas.

problem Understanding how diverse social value orientations affect behavior in sequential social dilemmas.
method Extending prior reinforcement learning studies, we instantiated heterogeneous SVO in a sequential social dilemma setting and measured task-specific diversity metrics.
result Heterogeneous SVO leads to meaningfully diverse policies across various incentive structures.

Paper tackles learning win-win solutions in aggregation systems.

problem Learning approximate equilibrium solutions in aggregation systems to keep suppliers.
method Multi-Agent Reinforcement Learning (MARL) with variance reduction mechanism.
result Approach reduces value variance and moves joint solution closer to Nash Equilibrium.

Algorithms are often used to produce decision-making rules that classify or evaluate individuals. When these individuals have incentives to be classified a certain way, they may behave strategically to influence their outcomes. We develop a model for how strategic agents can invest effort in order to change the outcome…

2018-07-13abs ↗pdf ↗

We study analytically and numerically Minority Games in which agents may invest in different assets (or markets), considering both the canonical and the grand-canonical versions. We find that the likelihood of agents trading in a given asset depends on the relative amount of information available in that market. More s…

2006-03-19abs ↗pdf ↗

Calibrated models can lead to miscalibrated aggregations in strategic interactions.

problem Miscalibration in aggregated predictions from multiple calibrated models.
method Analysis of strategic interactions between calibrated predictors, proving conditions for miscalibration and comparing VCG and Brier-score aggregation methods.
result VCG aggregation method outperforms Brier-score in strategic settings, providing robustness and comparable accuracy.

The paper proposes incentivizing human annotators with 'golden questions' to improve data quality.

problem Ensuring high-quality human annotations for training large language models.
method A principal-agent model is used to incentivize annotators with bonuses based on the maximum likelihood estimators (MLE) of their annotations. Hypothesis testing is applied to monitor the annotators' performance.
result The hypothesis testing rate for the principal-agent model is of Θ(1/nlogn)Θ(1/\sqrt{n \log n}), highlighting the importance of 'golden questions' for monitoring annotators.

We extend prior evidence that naively using intraday agent-based models that involve realistic order-matching processes for modeling continuous-time double auction markets seems to fail to be able to provide a robust link between data and many model parameters, even when these models are able to reproduce a number of w…

2016-11-25abs ↗pdf ↗

New method uses LP to achieve optimal sample complexity in multi-agent reinforcement learning.

problem Achieving global optimality in multi-agent reinforcement learning with average-cost criterion.
method Randomized Linear Programming and Stochastic Primal-Dual Methods for multi-agent saddle point problems.
result Sample complexity matches tight dependencies on state and action spaces, and scales with network size.

Algorithm learns optimal coordination for strategic agents in uncertain settings.

problem Optimizing rewards for strategic agents with private types and actions.
method Combines delaying mechanism, reward angle estimation, and LinUCB algorithm.
result Near optimal regret bound of O~(T)\tilde{O}(\sqrt{T}) for learning optimal policy.

Strategic feature manipulation helps learners identify meaningful variables in online regression settings.

problem Strategic feature manipulation poses a challenge for learners in online regression settings.
method Investigates how strategic feature manipulation by individuals can help learners recover meaningful features.
result Simple learner behavior can help accurately recover meaningful features and incentivize feature improvement.

No policy can simultaneously be fully autonomous, optimally calibrated, and helpful, proving a trilemma.

problem Proving impossibility of a policy achieving maximum helpfulness, optimal calibration, and full autonomy.
method Geometric proof showing that adding any non-affine autonomy incentive to a strictly proper scoring rule destroys strict properness.
result The Behavioral Credibility Trilemma: no policy can achieve all three goals simultaneously.

We refine toxicity bounds for dynamic liquidation incentives in CP-AMM systems.

problem Ensuring stability in dynamic liquidation incentives in automated market makers.
method Derived state-dependent toxicity bounds for dynamic liquidation incentives, reconciling them with CP-AMM price dynamics.
result State-dependent bounds and liquidity-depth-only condition for dynamic liquidation incentives.

Novel approach models opponent learning dynamics in multi-agent reinforcement learning.

problem Adaptation and learning of other agents in multi-agent settings cause non-stationarity, challenging existing algorithms.
method Develops a novel approach called Learning to Model Opponent Learning (LeMOL) to accurately model opponent learning dynamics.
result Structured opponent model is more accurate and stable than naive baselines.

Study optimal incentives for cleaner energy production.

problem Accelerate transition to cleaner technologies in energy market.
method Stochastic control models for three scenarios: single firm, two firms, and two firms without incentives.
result Optimal strategies for investment and production emerge, highlighting firm interactions and incentive effects.

Study shows how adaptive market agents can lead to persistent overpricing in financial markets.

problem Persistent overpricing in financial markets by adaptive market agents.
method Analyzes a repeated game between market maker and market taker, decomposes the game into competitive and collaborative components, and uses projected stochastic gradient ascent.
result Decentralized learning by adaptive market agents can lead to persistent overpricing in financial markets.

Two-stage mechanism designs reduce regret in recommender systems with stochastic covariates.

problem Designing effective recommender systems with user covariates sampled online.
method Two-stage algorithm integrating incentivized exploration with offline learning methods.
result Achieves sublinear regret while maintaining incentive compatibility.

Study assesses how much security restaking protocols need to pay for.

problem Determining the optimal security level for restaking protocols using token incentives.
method Expanding a model by Durvasula and Roughgarden to include strategic attackers and node operators, constructing an approximation algorithm for token-based incentives.
result Restaking protocols can be secure with proper incentive management, even against strategic adversaries.