A Machine With Human-Like Memory Systems
Not on the map. Why?
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.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 3 of its 9 references that are in the map. First posted on arXiv 4 Apr 2022.
Builds on
3 of 9 references.
References · 3
- 2016OpenAI Gymcited by 1,684
- 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
- 2019Episodic Memory Reader: Learning What to Remember for Question Answering from Streaming Datacited by 14
Built on by
Citing papers per year: 2024: 1; 2025: 0; 2026: 2.
3 papers.
- 2024"My agent understands me better": Integrating Dynamic Human-like Memory Recall and Consolidation in LLM-Based Agentscited by 29
- 2026Human-Inspired Context-Selective Multimodal Memory for Social Robotscited by 0
- 2026Improving Human-Robot Teamwork in Urban Search and Rescue Through Episodic Memory of Prior Collaborationcited by 0
- 2026Improving Human-Robot Teamwork in Urban Search and Rescue Through Episodic Memory of Prior Collaboration17 Jun 2026
- 2026Human-Inspired Context-Selective Multimodal Memory for Social Robots13 Apr 2026
- 2024"My agent understands me better": Integrating Dynamic Human-like Memory Recall and Consolidation in LLM-Based Agents31 Mar 2024