18 citations · 25 across the 2 of their papers we have counts for
2 papers
cs.LG2023★ 7 cited
Loss of Plasticity in Continual Deep Reinforcement Learning
Zaheer Abbas, Rosie Zhao, Joseph Modayil +2
The ability to learn continually is essential in a complex and changing world. In this paper, we characterize the behavior of canonical value-based deep reinforcement learning (RL)…
cs.LG2014★ 18 cited
Domain-Independent Optimistic Initialization for Reinforcement Learning
Marlos C. Machado, Sriram Srinivasan, Michael Bowling
In Reinforcement Learning (RL), it is common to use optimistic initialization of value functions to encourage exploration. However, such an approach generally depends on the domain…