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.

References in corpus (8)

• Transfer Learning in Deep Reinforcement Learning: A Survey
• Neural Episodic Control
• Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement
• Universal Successor Features Approximators
• Universal Successor Features for Transfer Reinforcement Learning
• State2vec: Off-Policy Successor Features Approximators
• Sample-Efficient Reinforcement Learning with Maximum Entropy Mellowmax Episodic Control
• Memory-Efficient Episodic Control Reinforcement Learning with Dynamic Online k-means