6 papers
Continual Reinforcement Learning with Neuroevolution
Eleni Nisioti, Andrea Cossu, Kathrin Korte +1
Despite many studies about causes and remedies of plasticity loss in Reinforcement Learning (RL) under continual task changes, no RL method has yet consistently achieved a good bal…
Where Decoder Cosine Similarity Fails for SAE Feature Flow Discovery
Hendrik Droste, Christian Medeiros Adriano, Kathrin Korte +1
Foundation models are increasingly adapted through fine-tuning, model editing, and alignment procedures while retaining previously acquired capabilities. Understanding the internal…
Dimensionality Controls When Modularity Helps in Continual Learning
Kathrin Korte, Christian Medeiros Adriano, Joachim Winther Pedersen +2
Compositional learning systems must balance plasticity, the ability to acquire new knowledge, with stability, the preservation of previously learned components, especially when tas…
When Does Structure Matter in Continual Learning? Dimensionality Controls When Modularity Shapes Representational Geometry
Kathrin Korte, Joachim Winter Pedersen, Eleni Nisioti +1
To preserve previously learned representations, continual learning systems must strike a balance between plasticity, the ability to acquire new knowledge, and stability. This stabi…
Hypernetworks That Evolve Themselves
Joachim Winther Pedersen, Erwan Plantec, Eleni Nisioti +4
How can neural networks evolve themselves without relying on external optimizers? We propose Self-Referential Graph HyperNetworks, systems where the very machinery of variation and…
Causal Knowledge Transfer for Multi-Agent Reinforcement Learning in Dynamic Environments
Kathrin Korte, Christian Medeiros Adriano, Sona Ghahremani +1
[Context] Multi-agent reinforcement learning (MARL) has achieved notable success in environments where agents must learn coordinated behaviors. However, transferring knowledge acro…