7 papers
CRRL: A Causality-Based Reinforcement Learning Framework for Autonomous System Recovery
Safia Fatima, Kai Olav Ellefsen, Leon Moonen
Traditional reinforcement learning (RL) for recovery in autonomous systems lacks causal understanding and generalizes poorly to novel failure scenarios. RL policies often stall in…
Memory-Efficient Policy Libraries with Low-Rank Adaptation in Reinforcement Learning
Samuel Valland Lyngset, Tor Viljen Raanaas, Gard Sveipe +4
When fine-tuning Large Language Models (LLMs), there has been success in minimizing both memory usage and computation with Parameter-Efficient Fine-Tuning (PEFT), like Low Rank Ada…
Lamarckian Inheritance in Dynamic Environments: How Key Variables Affect Evolutionary Dynamics
K. Ege de Bruin, Kyrre Glette, Kai Olav Ellefsen
The co-optimization of a robot's body and brain presents a coupled challenge: the morphology constrains which control strategies are effective, while the control determines how wel…
Social Learning Strategies for Evolved Virtual Soft Robots
K. Ege de Bruin, Kyrre Glette, Kai Olav Ellefsen +2
Optimizing the body and brain of a robot is a coupled challenge: the morphology determines what control strategies are effective, while the control parameters influence how well th…
Integrating Sample Inheritance into Bayesian Optimization for Evolutionary Robotics
K. Ege de Bruin, Kyrre Glette, Kai Olav Ellefsen
In evolutionary robotics, robot morphologies are designed automatically using evolutionary algorithms. This creates a body-brain optimization problem, where both morphology and con…
Generational Replacement and Learning for High-Performing and Diverse Populations in Evolvable Robots
K. Ege de Bruin, Kyrre Glette, Kai Olav Ellefsen
Evolutionary Robotics offers the possibility to design robots to solve a specific task automatically by optimizing their morphology and control together. However, this co-optimizat…