# A Machine With Human-Like Memory Systems

arXiv: https://arxiv.org/abs/2204.01611 · HTML: https://mlsanity.com/paper/2204.01611/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 9 references that are in the map.
- First posted on arXiv 4 Apr 2022.

## Builds on (most cited first, 3 of 3)

- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [Episodic Memory Reader: Learning What to Remember for Question Answering from Streaming Data](https://mlsanity.com/paper/1903.06164/) (2019)

## Built on by (most cited first, 3 of 3)

- ["My agent understands me better": Integrating Dynamic Human-like Memory Recall and Consolidation in LLM-Based Agents](https://mlsanity.com/paper/2404.00573/) (2024)
- [Human-Inspired Context-Selective Multimodal Memory for Social Robots](https://mlsanity.com/paper/2604.12081/) (2026)
- [Improving Human-Robot Teamwork in Urban Search and Rescue Through Episodic Memory of Prior Collaboration](https://mlsanity.com/paper/2606.18836/) (2026)

## Abstract (arXiv)

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.