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.

169,341 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “agent-participation”

When Crowdsourcing Meets Mobile Sensing: A Social Network Perspectivecs.SI

Crowdsourcing improves mobile sensing through social network trust.

problem Improving mobile sensing performance using agent-participatory data.

method Introducing crowdsourcing methods inspired by social networks.

result Improved mobile sensing performance via crowdsourcing.

crowdsourcing mobile sensing social networks agent-participation wisdom of crowds

2015-08-03abs ↗pdf ↗

Robust and Efficient Aggregation for Distributed Learningcs.LG

New aggregation methods improve robustness and efficiency in distributed learning.

problem Outliers and malicious agents compromise traditional averaging in distributed learning.

method Developed statistically efficient and robust aggregation schemes based on median and trimmed mean variations.

result Achieved higher sample efficiency compared to traditional robust aggregation schemes.

distributed learning aggregation robustness median trimmed mean

2022-04-01abs ↗pdf ↗

Asynchronous stochastic price pumpq-fin.TR

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.

Equity trading Asynchronous price updates Adaptive strategies Stationary returns Log-normal distribution

2018-09-25abs ↗pdf ↗

Taming the Exponential Action Set: Sublinear Regret and Fast Convergence to Nash Equilibrium in Online Congestion Gamescs.GT

Decentralized algorithm reduces regret and converges to Nash equilibrium in online congestion games.

problem Online congestion games with exponential action sets and strict Nash equilibria.

method CongestEXP algorithm using exponential weights method.

result CongestEXP achieves

O(kF\sqrt{T})

regret bound and almost exponential convergence to strict Nash equilibrium.

online games congestion games exponential weights regret minimization Nash equilibrium

2023-06-19abs ↗pdf ↗

LeDeepChef: Deep Reinforcement Learning Agent for Families of Text-Based Gamescs.LG

LeDeepChef learns to play multiple cooking games well.

problem Designing a general RL agent for multiple games of the same family.

method Actor-critic framework, action-space pruning, hierarchical RL, specialized module.

result LeDeepChef outperformed competitors on a diverse set of cooking games.

Reinforcement Learning Text-Based Games Cooking Hierarchical RL Action-space Pruning

2019-09-04abs ↗pdf ↗

Local and Global Explanations of Agent Behavior: Integrating Strategy Summaries with Saliency Mapscs.LG

Combining global and local explanations improves user understanding of RL agents.

problem Challenges in explaining agent behavior due to large state spaces and delayed rewards.

method Integrating strategy summaries with saliency maps to provide both global and local explanations.

result Summaries including important states significantly improve user understanding of RL agents.

Reinforcement Learning Agent Behavior Explanations Strategy Summaries Saliency Maps

2020-05-18abs ↗pdf ↗