Episodic Control

Episodic control in reinforcement learning aims to improve sample efficiency and learning speed by leveraging past experiences stored in an episodic memory. Current research focuses on developing efficient memory architectures, such as those incorporating encoder-decoder structures or state abstraction, and integrating episodic memory with various reinforcement learning algorithms, including deep Q-networks and model-based methods. These advancements are significant because they enable faster training and better generalization in complex tasks, with applications ranging from robotics and game playing to network security and natural language processing. The resulting improvements in sample efficiency and learning speed have broad implications across various fields.

Papers

March 18, 2024

Larimar: Large Language Models with Episodic Memory Control
Payel Das, Subhajit Chaudhury, Elliot Nelson, Igor Melnyk, Sarath Swaminathan, Sihui Dai, Aurélie Lozano, Georgios Kollias, Vijil Chenthamarakshan, Jiří, Navrátil, Soham Dan, Pin-Yu Chen
Anti Forgetting Episodic Memory Brain Inspired Length Generalization Episodic Control

March 2, 2024

Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning
Hyungho Na, Yunkyeong Seo, Il-chul Moon
Cooperative Multi Agent Reinforcement Learning Episodic Memory Episodic Control Episodic Reward

January 19, 2024

Episodic Reinforcement Learning with Expanded State-reward Space
Dayang Liang, Yaru Zhang, Yunlong Liu
Deep Reinforcement Learning Episodic Memory Episodic Reinforcement Learning Model Free Deep Reinforcement Learning Prompt Expansion State Reward Episodic Control

May 22, 2023

Yes, this Way! Learning to Ground Referring Expressions into Actions with Intra-episodic Feedback from Supportive Teachers
Philipp Sadler, Sherzod Hakimov, David Schlangen
Good Teacher New Way Past Action Reinforcement Learning Problem Referential Game Episodic Control Referring Expression Grounding Linguistic Signal

January 27, 2023

Neural Episodic Control with State Abstraction
Zhuo Li, Derui Zhu, Yujing Hu, Xiaofei Xie, Lei Ma, Yan Zheng, Yan Song, Yingfeng Chen, Jianjun Zhao
Episodic Memory State Abstraction Episodic Control

November 28, 2022

Continuous Episodic Control
Zhao Yang, Thomas M. Moerland, Mike Preuss, Aske Plaat
Episodic Memory Episodic Control Sparse Reward Continuous Control

September 3, 2022

Model-Free Deep Reinforcement Learning in Software-Defined Networks
Luke Borchjes, Clement Nyirenda, Louise Leenen
Deep Q Network Zero Sum Game Deep Reinforcement Learning Approach Model Free Deep Reinforcement Learning Software Defined Double Deep Q Network Episodic Control

January 4, 2022

Multi-Stage Episodic Control for Strategic Exploration in Text Games
Jens Tuyls, Shunyu Yao, Sham Kakade, Karthik Narasimhan
Reinforcement Learning Sparse Reward Text Based Game Exploration Exploitation Episodic Control

December 29, 2021

Sequential memory improves sample and memory efficiency in Episodic Control
Ismael T. Freire, Adrián F. Amil, Paul F. M. J. Verschure
External Sample Bio Inspired Episodic Reinforcement Learning Memory Efficiency Episodic Control Sequential Memory

November 4, 2021

Successor Feature Neural Episodic Control
David Emukpere, Xavier Alameda-Pineda, Chris Reinke
Reinforcement Learning Episodic Memory Single Agent Reinforcement Learning Episodic Control Generalized Policy Improvement

November 3, 2021

Model-Based Episodic Memory Induces Dynamic Hybrid Controls
Hung Le, Thommen Karimpanal George, Majid Abdolshah, Truyen Tran, Svetha Venkatesh
Reinforcement Learning Episodic Memory Habitual Behavior Episodic Control