Deepeka Garg
YOU?
Author Swipe
View article: Generating Structured Plan Representation of Procedures with LLMs
Generating Structured Plan Representation of Procedures with LLMs Open
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 operational inefficiencies. Traditional process modeling dema…
View article: Generative AI Agents for Knowledge Work Augmentation in Finance
Generative AI Agents for Knowledge Work Augmentation in Finance Open
The development of software agents that can autonomously take actions to achieve goals has been a long-standing foundational objective in the field of AI. Recent advances in generative AI have given rise to a new class of agents. These adv…
View article: Simulate and Optimise: A two-layer mortgage simulator for designing novel mortgage assistance products
Simulate and Optimise: A two-layer mortgage simulator for designing novel mortgage assistance products Open
We develop a novel two-layer approach for optimising mortgage relief products\nthrough a simulated multi-agent mortgage environment. While the approach is\ngeneric, here the environment is calibrated to the US mortgage market based on\npub…
View article: A Heterogeneous Agent Model of Mortgage Servicing: An Income-based Relief Analysis
A Heterogeneous Agent Model of Mortgage Servicing: An Income-based Relief Analysis Open
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 m…
View article: O3D: Offline Data-driven Discovery and Distillation for Sequential Decision-Making with Large Language Models
O3D: Offline Data-driven Discovery and Distillation for Sequential Decision-Making with Large Language Models Open
Recent advancements in large language models (LLMs) have exhibited promising performance in solving sequential decision-making problems. By imitating few-shot examples provided in the prompts (i.e., in-context learning), an LLM agent can i…
View article: Phantom -- A RL-driven multi-agent framework to model complex systems
Phantom -- A RL-driven multi-agent framework to model complex systems Open
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 interac…
View article: Autonomous traffic signal control using deep reinforcement learning
Autonomous traffic signal control using deep reinforcement learning Open
Traffic signals provide one of the primary means to administer conflicting road traffic flows. The efficiency of road transportation systems significantly depends on signal operation. The state of-the-art signal control strategies are unab…
View article: Traffic3D: A New Traffic Simulation Paradigm
Traffic3D: A New Traffic Simulation Paradigm Open
The field of Deep Reinforcement Learning has evolved significantly over the last few years. However, an important and not yet fully-attained goal is to produce intelligent agents which can be successfully taken out of the laboratory and em…