Keywords: Reinforcement Learning, Transfer Learning, Sample Efficiency, Episodic Control, Successor Features
TL;DR: A reinforcement learning framework merging sample efficiency using episodic control with meta learning using successor features
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.
Contribution Process Agreement: Yes
Poster Session Selection: Poster session #2 (16:50 UTC+1)