8 papers · 1 filter
Deep Reinforcement Learning for Dynamic Algorithm Configuration: A Case Study on Optimizing OneMax with the (1+(,))-GA
Tai Nguyen, Phong Le, André Biedenkapp +2
Dynamic Algorithm Configuration (DAC) studies the efficient identification of control policies for parameterized optimization algorithms. Numerous studies leverage Reinforcement Le…
A Llama walks into the 'Bar': Efficient Supervised Fine-Tuning for Legal Reasoning in the Multi-state Bar Exam
Rean Fernandes, André Biedenkapp, Frank Hutter +1
Legal reasoning tasks present unique challenges for large language models (LLMs) due to the complexity of domain-specific knowledge and reasoning processes. This paper investigates…
On the Importance of Reward Design in Reinforcement Learning-based Dynamic Algorithm Configuration: A Case Study on OneMax with (1+(,))-GA
Tai Nguyen, Phong Le, André Biedenkapp +2
Dynamic Algorithm Configuration (DAC) has garnered significant attention in recent years, particularly in the prevalence of machine learning and deep learning algorithms. Numerous…
One-shot World Models Using a Transformer Trained on a Synthetic Prior
Fabio Ferreira, Moreno Schlageter, Raghu Rajan +2
A World Model is a compressed spatial and temporal representation of a real world environment that allows one to train an agent or execute planning methods. However, world models a…
CANDID DAC: Leveraging Coupled Action Dimensions with Importance Differences in DAC
Philipp Bordne, M. Asif Hasan, Eddie Bergman +2
High-dimensional action spaces remain a challenge for dynamic algorithm configuration (DAC). Interdependencies and varying importance between action dimensions are further known ke…
Dreaming of Many Worlds: Learning Contextual World Models Aids Zero-Shot Generalization
Sai Prasanna, Karim Farid, Raghu Rajan +1
Zero-shot generalization (ZSG) to unseen dynamics is a major challenge for creating generally capable embodied agents. To address the broader challenge, we start with the simpler s…