16 citations · 32 across the 19 of their papers we have counts for
20 papers
Entropy-informed Decoding: Adaptive Information-Driven Branching
Benjamin Patrick Evans, Sumitra Ganesh, Leo Ardon
Large language models (LLMs) achieve remarkable generative performance, yet their output quality is dependent on the decoding strategy. While sampling-based methods (e.g., top-k, n…
AgentCrypt: Advancing Privacy and (Secure) Computation in AI Agent Collaboration
Harish Karthikeyan, Yue Guo, Leo de Castro +5
As AI agents increasingly operate in complex environments, ensuring reliable, context-aware privacy is critical for regulatory compliance. Traditional access controls are insuffici…
PADME: Procedure Aware DynaMic Execution
Deepeka Garg, Sihan Zeng, Annapoorani L. Narayanan +2
Learning to autonomously execute long-horizon procedures from natural language remains a core challenge for intelligent agents. Free-form instructions such as recipes, scientific p…
Downside Risk-Aware Equilibria for Strategic Decision-Making
Oliver Slumbers, Benjamin Patrick Evans, Sumitra Ganesh +1
Game theory has traditionally had a relatively limited view of risk based on how a player's expected reward is impacted by the uncertainty of the actions of other players. Recently…
Learning in Stackelberg Mean Field Games: A Non-Asymptotic Analysis
Sihan Zeng, Benjamin Patrick Evans, Sujay Bhatt +3
We study policy optimization in Stackelberg mean field games (MFGs), a hierarchical framework for modeling the strategic interaction between a single leader and an infinitely large…
Modelling bounded rational decision-making through Wasserstein constraints
Benjamin Patrick Evans, Leo Ardon, Sumitra Ganesh
Modelling bounded rational decision-making through information constrained processing provides a principled approach for representing departures from rationality within a reinforce…
Generating Structured Plan Representation of Procedures with LLMs
Deepeka Garg, Sihan Zeng, Sumitra Ganesh +1
In this paper, we address the challenges of managing Standard Operating Procedures (SOPs), which often suffer from inconsistencies in language, format, and execution, leading to op…
FORM: Learning Expressive and Transferable First-Order Logic Reward Machines
Leo Ardon, Daniel Furelos-Blanco, Roko Parac +1
Reward machines (RMs) are an effective approach for addressing non-Markovian rewards in reinforcement learning (RL) through finite-state machines. Traditional RMs, which label edge…
ADAGE: A generic two-layer framework for adaptive agent based modelling
Benjamin Patrick Evans, Sihan Zeng, Sumitra Ganesh +1
Agent-based models (ABMs) are valuable for modelling complex, potentially out-of-equilibria scenarios. However, ABMs have long suffered from the Lucas critique, stating that agent…
Simulate and Optimise: A two-layer mortgage simulator for designing novel mortgage assistance products
Leo Ardon, Benjamin Patrick Evans, Deepeka Garg +3
We develop a novel two-layer approach for optimising mortgage relief products through a simulated multi-agent mortgage environment. While the approach is generic, here the environm…
Learning Robust Reward Machines from Noisy Labels
Roko Parac, Lorenzo Nodari, Leo Ardon +3
This paper presents PROB-IRM, an approach that learns robust reward machines (RMs) for reinforcement learning (RL) agents from noisy execution traces. The key aspect of RM-driven R…
On the Sample Efficiency of Abstractions and Potential-Based Reward Shaping in Reinforcement Learning
Giuseppe Canonaco, Leo Ardon, Alberto Pozanco +1
The use of Potential-Based Reward Shaping (PBRS) has shown great promise in the ongoing research effort to tackle sample inefficiency in Reinforcement Learning (RL). However, choos…
A Heterogeneous Agent Model of Mortgage Servicing: An Income-based Relief Analysis
Deepeka Garg, Benjamin Patrick Evans, Leo Ardon +5
Mortgages account for the largest portion of household debt in the United States, totaling around $12 trillion nationwide. In times of financial hardship, alleviating mortgage bur…
Learning Reward Machines in Cooperative Multi-Agent Tasks
Leo Ardon, Daniel Furelos-Blanco, Alessandra Russo
This paper presents a novel approach to Multi-Agent Reinforcement Learning (MARL) that combines cooperative task decomposition with the learning of reward machines (RMs) encoding t…
Inapplicable Actions Learning for Knowledge Transfer in Reinforcement Learning
Leo Ardon, Alberto Pozanco, Daniel Borrajo +1
Reinforcement Learning (RL) algorithms are known to scale poorly to environments with many available actions, requiring numerous samples to learn an optimal policy. The traditional…
Towards Multi-Agent Reinforcement Learning driven Over-The-Counter Market Simulations
Nelson Vadori, Leo Ardon, Sumitra Ganesh +7
We study a game between liquidity provider and liquidity taker agents interacting in an over-the-counter market, for which the typical example is foreign exchange. We show how a su…
Phantom -- A RL-driven multi-agent framework to model complex systems
Leo Ardon, Jared Vann, Deepeka Garg +2
Agent based modelling (ABM) is a computational approach to modelling complex systems by specifying the behaviour of autonomous decision-making components or agents in the system an…
Reinforcement Learning to Solve NP-hard Problems: an Application to the CVRP
Leo Ardon
In this paper, we evaluate the use of Reinforcement Learning (RL) to solve a classic combinatorial optimization problem: the Capacitated Vehicle Routing Problem (CVRP). We formaliz…
Towards a Fairer Digital Marketing Model
Leo Ardon, Dario Morelli, Francesco Villani +1
Surfing on the internet boom, the digital marketing industry has seen an exponential growth in the recent years and is often at the origin of the financial success of the biggest t…
Towards a fully RL-based Market Simulator
Leo Ardon, Nelson Vadori, Thomas Spooner +3
We present a new financial framework where two families of RL-based agents representing the Liquidity Providers and Liquidity Takers learn simultaneously to satisfy their objective…