33 citations · 45 across the 7 of their papers we have counts for
4 papers · 1 filter
Frequency and Generalisation of Periodic Activation Functions in Reinforcement Learning
Augustine N. Mavor-Parker, Matthew J. Sargent, Caswell Barry +2
Periodic activation functions, often referred to as learned Fourier features have been widely demonstrated to improve sample efficiency and stability in a variety of deep RL algori…
Towards Automated Circuit Discovery for Mechanistic Interpretability
Arthur Conmy, Augustine N. Mavor-Parker, Aengus Lynch +2
Through considerable effort and intuition, several recent works have reverse-engineered nontrivial behaviors of transformer models. This paper systematizes the mechanistic interpre…
Using Forwards-Backwards Models to Approximate MDP Homomorphisms
Augustine N. Mavor-Parker, Matthew J. Sargent, Christian Pehle +3
Reinforcement learning agents must painstakingly learn through trial and error what sets of state-action pairs are value equivalent -- requiring an often prohibitively large amount…
How to Stay Curious while Avoiding Noisy TVs using Aleatoric Uncertainty Estimation
Augustine N. Mavor-Parker, Kimberly A. Young, Caswell Barry +1
Exploration in environments with sparse rewards is difficult for artificial agents. Curiosity driven learning -- using feed-forward prediction errors as intrinsic rewards -- has ac…