5 citations · 9 across the 6 of their papers we have counts for
7 papers
Task-Induced Representational Invariances Depend on Learning Objective in Deep RL
Manu Srinath Halvagal, Sebastian Lee, SueYeon Chung
Reinforcement Learning (RL) has long served as a model for goal-directed animal behavior in neuroscience. Modern deep RL has shown remarkable success across many domains, further s…
Uncertainty Prioritized Experience Replay
Rodrigo Carrasco-Davis, Sebastian Lee, Claudia Clopath +1
Prioritized experience replay, which improves sample efficiency by selecting relevant transitions to update parameter estimates, is a crucial component of contemporary value-based…
A Theory of Initialisation's Impact on Specialisation
Devon Jarvis, Sebastian Lee, Clémentine Carla Juliette Dominé +2
Prior work has demonstrated a consistent tendency in neural networks engaged in continual learning tasks, wherein intermediate task similarity results in the highest levels of cata…
Lifelong Reinforcement Learning via Neuromodulation
Sebastian Lee, Samuel Liebana, Claudia Clopath +1
Navigating multiple tasks$\unicode{x2014}$for instance in succession as in continual or lifelong learning, or in distributions as in meta or multi-task learning$\unicode{x2014}$req…
The RL Perceptron: Generalisation Dynamics of Policy Learning in High Dimensions
Nishil Patel, Sebastian Lee, Stefano Sarao Mannelli +2
Reinforcement learning (RL) algorithms have proven transformative in a range of domains. To tackle real-world domains, these systems often use neural networks to learn policies dir…
Maslow's Hammer for Catastrophic Forgetting: Node Re-Use vs Node Activation
Sebastian Lee, Stefano Sarao Mannelli, Claudia Clopath +2
Continual learning - learning new tasks in sequence while maintaining performance on old tasks - remains particularly challenging for artificial neural networks. Surprisingly, the…
Continual Learning in the Teacher-Student Setup: Impact of Task Similarity
Sebastian Lee, Sebastian Goldt, Andrew Saxe
Continual learning-the ability to learn many tasks in sequence-is critical for artificial learning systems. Yet standard training methods for deep networks often suffer from catast…