7 citations · 13 across the 9 of their papers we have counts for
Showing 2024Show all
3 papers · 1 filter
cs.LG2024★ 1 cited
Weight Clipping for Deep Continual and Reinforcement Learning
Mohamed Elsayed, Qingfeng Lan, Clare Lyle +1
Many failures in deep continual and reinforcement learning are associated with increasing magnitudes of the weights, making them hard to change and potentially causing overfitting.…
cs.LG2024★ 1 cited
More Efficient Randomized Exploration for Reinforcement Learning via Approximate Sampling
Haque Ishfaq, Yixin Tan, Yu Yang +5
Thompson sampling (TS) is one of the most popular exploration techniques in reinforcement learning (RL). However, most TS algorithms with theoretical guarantees are difficult to im…
cs.LG2024★ 1 cited
Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning
Mohamed Elsayed, A. Rupam Mahmood
Deep representation learning methods struggle with continual learning, suffering from both catastrophic forgetting of useful units and loss of plasticity, often due to rigid and un…