HyperAIHyperAI

Command Palette

Search for a command to run...

5 months ago

A Machine With Human-Like Memory Systems

Taewoon Kim; Michael Cochez; Vincent Francois-Lavet; Mark Neerincx; Piek Vossen

A Machine With Human-Like Memory Systems

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.

Code Repositories

humemai/agent-room-env-v0
Official
Mentioned in GitHub

Benchmarks

BenchmarkMethodologyMetrics
roomenv-v0-on-roomenv-v0HumemAI-v0-handcrafted-capacity=32
final agent reward: 700

Build AI with AI

From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.

AI Co-coding
Ready-to-use GPUs
Best Pricing
Get Started

Hyper Newsletters

Subscribe to our latest updates
We will deliver the latest updates of the week to your inbox at nine o'clock every Monday morning
Powered by MailChimp
A Machine With Human-Like Memory Systems | Papers | HyperAI