7 citations · 7 across the 1 of their papers we have counts for
4 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…
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…