papers

Publications (12)

cs.LG2024

Structure in Deep Reinforcement Learning: A Survey and Open Problems

Aditya Mohan, Amy Zhang, Marius Lindauer

Reinforcement Learning (RL), bolstered by the expressive capabilities of Deep Neural Networks (DNNs) for function approximation, has demonstrated considerable success in numerous a…

cs.LG2023

Learning Activation Functions for Sparse Neural Networks

Mohammad Loni, Aditya Mohan, Mehdi Asadi +1

Sparse Neural Networks (SNNs) can potentially demonstrate similar performance to their dense counterparts while saving significant energy and memory at inference. However, the accu…

cs.LG2023

Contextualize Me -- The Case for Context in Reinforcement Learning

Carolin Benjamins, Theresa Eimer, Frederik Schubert +6

While Reinforcement Learning ( RL) has made great strides towards solving increasingly complicated problems, many algorithms are still brittle to even slight environmental changes.…

cs.LG2024

Instance Selection for Dynamic Algorithm Configuration with Reinforcement Learning: Improving Generalization

Carolin Benjamins, Gjorgjina Cenikj, Ana Nikolikj +3

Dynamic Algorithm Configuration (DAC) addresses the challenge of dynamically setting hyperparameters of an algorithm for a diverse set of instances rather than focusing solely on i…

cs.RO2026

EquiBim: Learning Symmetry-Equivariant Policy for Bimanual Manipulation

Zhiyuan Zhang, Aditya Mohan, Seungho Han +3

Robotic imitation learning has achieved impressive success in learning complex manipulation behaviors from demonstrations. However, many existing robot learning methods do not expl…

cs.LG2023

AutoRL Hyperparameter Landscapes

Aditya Mohan, Carolin Benjamins, Konrad Wienecke +2

Although Reinforcement Learning (RL) has shown to be capable of producing impressive results, its use is limited by the impact of its hyperparameters on performance. This often mak…

cs.LG2022

Towards Meta-learned Algorithm Selection using Implicit Fidelity Information

Aditya Mohan, Tim Ruhkopf, Marius Lindauer

Automatically selecting the best performing algorithm for a given dataset or ranking multiple algorithms by their expected performance supports users in developing new machine lear…

cs.LG2026

ARLBench: Flexible and Efficient Benchmarking for Hyperparameter Optimization in Reinforcement Learning

Jannis Becktepe, Julian Dierkes, Carolin Benjamins +7

Hyperparameters are a critical factor in reliably training well-performing reinforcement learning (RL) agents. Unfortunately, developing and evaluating automated approaches for tun…

cs.LG2026

Moments Matter:Stabilizing Policy Optimization using Return Distributions

Dennis Jabs, Aditya Mohan, Marius Lindauer

Deep Reinforcement Learning (RL) agents often learn policies that achieve the same episodic return yet behave very differently, due to a combination of environmental (random transi…

cs.AI2026

Multi-Sensor Alignment for Weather Simulations

Samsad Alam, Devyani Lambhate, Aditya Mohan +2

The paper introduces methods to align weather simulations across multiple sensors for autonomous vehicle perception, including ReDAM for fog intensity and Unified-weather-edit for…

#weather simulation#sensor alignment#autonomous vehicles#3d object detection
cs.LG2024

AutoML in the Age of Large Language Models: Current Challenges, Future Opportunities and Risks

Alexander Tornede, Difan Deng, Theresa Eimer +8

The fields of both Natural Language Processing (NLP) and Automated Machine Learning (AutoML) have achieved remarkable results over the past years. In NLP, especially Large Language…

cs.LG2026

Beyond Success Rates: Trainability and Extractability for Offline GCRL

Jan Malte Töpperwien, Aditya Mohan, Marius Lindauer

Offline goal-conditioned reinforcement learning (GCRL) is typically benchmarked by the best tuned success rate of each method. This score measures attainable performance, but it do…