7 citations · 13 across the 9 of their papers we have counts for
7 papers · 1 filter
Efficient Reinforcement Learning by Reducing Forgetting with Elephant Activation Functions
Qingfeng Lan, Gautham Vasan, A. Rupam Mahmood
Catastrophic forgetting has remained a significant challenge for efficient reinforcement learning for decades (Ring 1994, Rivest and Precup 2003). While recent works have proposed…
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.…
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…
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…
Elephant Neural Networks: Born to Be a Continual Learner
Qingfeng Lan, A. Rupam Mahmood
Catastrophic forgetting remains a significant challenge to continual learning for decades. While recent works have proposed effective methods to mitigate this problem, they mainly…
Maintaining Plasticity in Deep Continual Learning
Shibhansh Dohare, J. Fernando Hernandez-Garcia, Parash Rahman +2
Modern deep-learning systems are specialized to problem settings in which training occurs once and then never again, as opposed to continual-learning settings in which training occ…
Learning to Optimize for Reinforcement Learning
Qingfeng Lan, A. Rupam Mahmood, Shuicheng Yan +1
In recent years, by leveraging more data, computation, and diverse tasks, learned optimizers have achieved remarkable success in supervised learning, outperforming classical hand-d…