Toward Good Abstractions for Lifelong Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Building a Subspace of Policies for Scalable Continual Learning (2022, background): “There is also a large body of work which leverages the shared structure of the tasks [50, 30, 25, 27, 1, 43], meta-learning [19, 44, 4, 8, 33, 52, 39], or generative models [35, 42, 41, 2] to improve CRL agents, but these are less related to CSP and not very competitive.”
State Abstractions for Lifelong Reinforcement Learning (2018, background): “We draw a parallel between these results and those presented in our previous work (Abel et al., 2017), where we identify the existence of cases where the beneﬁts of generalization that come with state abstractions are accompanied by more challenging exploration and credit-assignment problems.”