20 citations · 35 across the 5 of their papers we have counts for
5 papers
Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem
Maciej Wołczyk, Bartłomiej Cupiał, Mateusz Ostaszewski +5
Fine-tuning is a widespread technique that allows practitioners to transfer pre-trained capabilities, as recently showcased by the successful applications of foundation models. How…
Exploiting Novel GPT-4 APIs
Kellin Pelrine, Mohammad Taufeeque, Michał Zając +2
Language model attacks typically assume one of two extreme threat models: full white-box access to model weights, or black-box access limited to a text generation API. However, rea…
Prediction Error-based Classification for Class-Incremental Learning
Michał Zając, Tinne Tuytelaars, Gido M. van de Ven
Class-incremental learning (CIL) is a particularly challenging variant of continual learning, where the goal is to learn to discriminate between all classes presented in an increme…
Disentangling Transfer in Continual Reinforcement Learning
Maciej Wołczyk, Michał Zając, Razvan Pascanu +2
The ability of continual learning systems to transfer knowledge from previously seen tasks in order to maximize performance on new tasks is a significant challenge for the field, l…
Continual World: A Robotic Benchmark For Continual Reinforcement Learning
Maciej Wołczyk, Michał Zając, Razvan Pascanu +2
Continual learning (CL) -- the ability to continuously learn, building on previously acquired knowledge -- is a natural requirement for long-lived autonomous reinforcement learning…