4 papers
Spectral Collapse Drives Loss of Plasticity in Deep Continual Learning
Arjun Prakash, Naicheng He, Kaicheng Guo +5
We investigate why deep neural networks suffer from loss of plasticity in continual learning, and thus fail to learn new tasks without reinitializing parameters. We show that this…
JAXenstein: Accelerated Benchmarking for First-Person Environments
Ruo Yu Tao, George Konidaris
The progression of reinforcement learning algorithms have been driven by challenging benchmarks. The rate in which a researcher can iterate on a problem setting directly impacts th…
Benchmarking Partial Observability in Reinforcement Learning with a Suite of Memory-Improvable Domains
Ruo Yu Tao, Kaicheng Guo, Cameron Allen +1
Mitigating partial observability is a necessary but challenging task for general reinforcement learning algorithms. To improve an algorithm's ability to mitigate partial observabil…
Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancy
Cameron Allen, Aaron Kirtland, Ruo Yu Tao +7
Reinforcement learning algorithms typically rely on the assumption that the environment dynamics and value function can be expressed in terms of a Markovian state representation. H…