Skip to Main content Skip to Navigation
New interface
Conference papers

Successor Feature Neural Episodic Control

Abstract : A longstanding goal in reinforcement learning is to build intelligent agents that show fast learning and a flexible transfer of skills akin to humans and animals. This paper investigates the integration of two frameworks for tackling those goals: episodic control and successor features. Episodic control is a cognitively inspired approach relying on episodic memory, an instance-based memory model of an agent's experiences. Meanwhile, successor features and generalized policy improvement (SF&GPI) is a meta and transfer learning framework allowing to learn policies for tasks that can be efficiently reused for later tasks which have a different reward function. Individually, these two techniques have shown impressive results in vastly improving sample efficiency and the elegant reuse of previously learned policies. Thus, we outline a combination of both approaches in a single reinforcement learning framework and empirically illustrate its benefits.
Document type :
Conference papers
Complete list of metadata

https://hal.inria.fr/hal-03426874
Contributor : Xavier Alameda-Pineda Connect in order to contact the contributor
Submitted on : Friday, November 12, 2021 - 4:10:46 PM
Last modification on : Wednesday, May 4, 2022 - 12:00:02 PM

Links full text

Identifiers

  • HAL Id : hal-03426874, version 1
  • ARXIV : 2111.03110

Collections

Citation

David Emukpere, Xavier Alameda-Pineda, Chris Reinke. Successor Feature Neural Episodic Control. NeurIPS 2021 - 35th International Conference on Neural Information Processing Systems, Dec 2021, Virtual, Canada. pp.1-12. ⟨hal-03426874⟩

Share

Metrics

Record views

72