Zobrazeno 1 - 10
of 22
pro vyhledávání: '"Ardon, Leo"'
Autor:
Ardon, Leo, Evans, Benjamin Patrick, Garg, Deepeka, Narayanan, Annapoorani Lakshmi, Henry-Nickie, Makada, Ganesh, Sumitra
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 environment is calibrated to the US mortgage market based on publicly availabl
Externí odkaz:
http://arxiv.org/abs/2411.00563
Autor:
Parac, Roko, Nodari, Lorenzo, Ardon, Leo, Furelos-Blanco, Daniel, Cerutti, Federico, Russo, Alessandra
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 RL is the exploitation of a finite-state machine that decomposes the ag
Externí odkaz:
http://arxiv.org/abs/2408.14871
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, the choice of the potential function is critical for this technique to be e
Externí odkaz:
http://arxiv.org/abs/2404.07826
Autor:
Garg, Deepeka, Evans, Benjamin Patrick, Ardon, Leo, Narayanan, Annapoorani Lakshmi, Vann, Jared, Madhushani, Udari, Henry-Nickie, Makada, Ganesh, Sumitra
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 burdens is essential for supporting affected households. The mortgage ser
Externí odkaz:
http://arxiv.org/abs/2402.17932
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 the structure of the sub-tasks. The proposed method helps deal with the
Externí odkaz:
http://arxiv.org/abs/2303.14061
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 approach of considering the same fixed action space in every possible
Externí odkaz:
http://arxiv.org/abs/2211.15589
Autor:
Vadori, Nelson, Ardon, Leo, Ganesh, Sumitra, Spooner, Thomas, Amrouni, Selim, Vann, Jared, Xu, Mengda, Zheng, Zeyu, Balch, Tucker, Veloso, Manuela
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 suitable design of parameterized families of reward functions coupled wi
Externí odkaz:
http://arxiv.org/abs/2210.07184
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 and allowing the system dynamics to emerge from their interactions. Rece
Externí odkaz:
http://arxiv.org/abs/2210.06012
Autor:
Ardon, Leo
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 formalize this problem in the RL framework and compare two of the most promisi
Externí odkaz:
http://arxiv.org/abs/2201.05393
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 tech firms. In this paper we study the current landscape of this indust
Externí odkaz:
http://arxiv.org/abs/2201.05368