A Machine With Human-Like Memory Systems

2022/04/04 by Taewoon Kim, Kim, Taewoon, Michael Cochez +7 · 1 citation
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Reinforcement Learning in Robotics #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2204.01611

openalex publication_date 2022/04/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01

Abstract

Inspired by the cognitive science theory, we explicitly model an agent with both semantic and episodic memory systems, and show that it is better than having just one of the two memory systems. In order to show this, we have designed and released our own challenging environment, "the Room", compatible with OpenAI Gym, where an agent has to properly learn how to encode, store, and retrieve memories to maximize its rewards. The Room environment allows for a hybrid intelligence setup where machines and humans can collaborate. We show that two agents collaborating with each other results in better performance than one agent acting alone.

Cited by

• Improving Human-Robot Teamwork in Urban Search and Rescue Through Episodic Memory of Prior Collaboration

Related

• AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents
• Memory and attention in deep learning
• Toward Human-Level Artificial Intelligence
• A Cognitive Architecture for Machine Consciousness and Artificial Superintelligence: Thought Is Structured by the Iterative Updating of Working Memory
• A Proposal for Intelligent Agents with Episodic Memory