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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyemukpere2021successor

Related papers

• Successor Features Combine Elements Of Model-free And Model-based Reinforcement Learning (2019)0.00
• Successor Feature Sets: Generalizing Successor Representations Across Policies (2021)5.84
• Successor Feature Representations (2021)0.00
• Successor Features For Transfer In Reinforcement Learning (2016)0.00
• Advantages And Limitations Of Using Successor Features For Transfer In Reinforcement Learning (2017)0.00
• Successor Features For Transfer In Alternating Markov Games (2025)0.00
• SF-DQN: Provable Knowledge Transfer Using Successor Feature For Deep Reinforcement Learning (2024)0.00
• A New Representation Of Successor Features For Transfer Across Dissimilar Environments (2021)0.00