DL
D. Lentschig
info
Please Note
<p>This page displays the records of the person named above and is not linked to a unique person identifier. This record may need to be merged to a profile.</p>
2 records found
1
Can we use LLMs for abstraction in MDPs?
A deep dive into the potential and limitations of LLMs
This thesis explores whether Large Language Models (LLMs) can generate abstractions in Markovian Decision Processes (MDPs) to reduce complexity in planning with Monte Carlo Tree Search (MCTS). A complete pipeline was developed to extract and validate cluster-based abstractions from LLMs. The pipeline combines modular prompt engineering, post-processing, and evaluation through both structural similarity and performance metrics. Experiments in gridworld environments show that Deepseek-R1 models consistently outperform LLaMA models, with architecture and training proving more important than parameter size. Structured prompts, especially those using JSON representation and rationale-driven responses, significantly improved abstraction quality. While LLMs can approximate, and sometimes even find the ideal abstractions in simple environments, performance deteriorates in larger or less regular domains. These findings highlight both the potential and current limitations of LLM-based abstraction, and suggest directions for future research, including more complex environments, richer abstraction types, and advanced prompting strategies.
...
This thesis explores whether Large Language Models (LLMs) can generate abstractions in Markovian Decision Processes (MDPs) to reduce complexity in planning with Monte Carlo Tree Search (MCTS). A complete pipeline was developed to extract and validate cluster-based abstractions from LLMs. The pipeline combines modular prompt engineering, post-processing, and evaluation through both structural similarity and performance metrics. Experiments in gridworld environments show that Deepseek-R1 models consistently outperform LLaMA models, with architecture and training proving more important than parameter size. Structured prompts, especially those using JSON representation and rationale-driven responses, significantly improved abstraction quality. While LLMs can approximate, and sometimes even find the ideal abstractions in simple environments, performance deteriorates in larger or less regular domains. These findings highlight both the potential and current limitations of LLM-based abstraction, and suggest directions for future research, including more complex environments, richer abstraction types, and advanced prompting strategies.
Bachelor thesis
(2022)
-
D. Canosa Ybarra, K.I. Janisch, N. Kalis, D. Lentschig, A. Lopez Rivera, M. Manieri, Kim Regnery, T.L. van der Wal, G. Gonzalez Saiz, O. Yuksel, Lorenza Mottinelli, J.A. Melkert, A. Menicucci
Solutions for reducing greenhouse gas emissions are paramount under the current environmental circumstances. With methane and carbon dioxide being the most critical emission gasses, SigmaSat set out to find a way to reduce these emissions and simultaneously fulfill its scientific mission. While executing the scientific mission of designing a small satellite mission to demonstrate the latest advances in artificial intelligence, SigmaSat managed to devise a design that allows players in the energy production industry (such as refineries) to drastically reduce their methane and CO2 emissions.
...
Solutions for reducing greenhouse gas emissions are paramount under the current environmental circumstances. With methane and carbon dioxide being the most critical emission gasses, SigmaSat set out to find a way to reduce these emissions and simultaneously fulfill its scientific mission. While executing the scientific mission of designing a small satellite mission to demonstrate the latest advances in artificial intelligence, SigmaSat managed to devise a design that allows players in the energy production industry (such as refineries) to drastically reduce their methane and CO2 emissions.