Evolving hierarchical memory-prediction machines in multi-task reinforcement learning

Kelly, Stephen W.; Voegerl, Tatiana; Banzhaf, Wolfgang; Gondro, Cedric

doi:10.1007/s10710-021-09418-4

Cited by 11 publications

(1 citation statement)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In general, the goal is to enable transfer learning between policies, which, however, omits the capacity for forgetting or re-adaptation. Some works assume a static objective [93,94,95,96,97], others a static agent and/or environment [98,99,100] or none of both [101,102,103]. In contrast, multi-agent reinforcement learning is mostly related to some kind of joint training and is hence not related to CL.…”

Section: Existing Approachesmentioning

confidence: 99%

Tutorial - Continual Learning beyond classification

Gepperth¹,

Lesort²

2022

ESANN 2022 Proceedings

View full text Add to dashboard Cite

Continual Learning (CL, sometimes also termed incremental learning) is a flavor of machine learning where the usual assumption of stationary data distribution is relaxed or omitted. When naively applying, e.g., DNNs in CL problems, changes in the data distribution can cause the so-called catastrophic forgetting (CF) effect: an abrupt loss of previous knowledge. Although many significant contributions to enabling CL have been made in recent years, most works address supervised (classification) problems. This article reviews literature that study CL in other settings, such as learning with reduced supervision, fully unsupervised learning, and reinforcement learning. Besides proposing a simple schema for classifying CL approaches w.r.t. their level of autonomy and supervision, we discuss the specific challenges associated with each setting and the potential contributions to the field of CL in general. Framework and Goals of Continual LearningContinual learning (CL) is a machine learning sub-field that studies learning under time-varying data distributions. This relaxes one of the fundamental assumptions of statistical learning theory ([1]), which states that the data follows 67

show abstract