A Machine with Short-Term, Episodic, and Semantic Memory Systems
- URL: http://arxiv.org/abs/2212.02098v2
- Date: Sat, 8 Jul 2023 10:50:19 GMT
- Title: A Machine with Short-Term, Episodic, and Semantic Memory Systems
- Authors: Taewoon Kim, Michael Cochez, Vincent Fran\c{c}ois-Lavet, Mark
Neerincx, Piek Vossen
- Abstract summary: Inspired by the cognitive science theory of the explicit human memory systems, we have modeled an agent with short-term, episodic, and semantic memory systems.
Our experiments indicate that an agent with human-like memory systems can outperform an agent without this memory structure in the environment.
- Score: 4.6862970461449605
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Inspired by the cognitive science theory of the explicit human memory
systems, we have modeled an agent with short-term, episodic, and semantic
memory systems, each of which is modeled with a knowledge graph. To evaluate
this system and analyze the behavior of this agent, we designed and released
our own reinforcement learning agent environment, "the Room", where an agent
has to learn how to encode, store, and retrieve memories to maximize its return
by answering questions. We show that our deep Q-learning based agent
successfully learns whether a short-term memory should be forgotten, or rather
be stored in the episodic or semantic memory systems. Our experiments indicate
that an agent with human-like memory systems can outperform an agent without
this memory structure in the environment.
Related papers
- A Survey on the Memory Mechanism of Large Language Model based Agents [66.4963345269611]
Large language model (LLM) based agents have recently attracted much attention from the research and industry communities.
LLM-based agents are featured in their self-evolving capability, which is the basis for solving real-world problems.
The key component to support agent-environment interactions is the memory of the agents.
arXiv Detail & Related papers (2024-04-21T01:49:46Z) - In-Memory Learning: A Declarative Learning Framework for Large Language
Models [56.62616975119192]
We propose a novel learning framework that allows agents to align with their environment without relying on human-labeled data.
This entire process transpires within the memory components and is implemented through natural language.
We demonstrate the effectiveness of our framework and provide insights into this problem.
arXiv Detail & Related papers (2024-03-05T08:25:11Z) - Evaluating Long-Term Memory in 3D Mazes [10.224858246626171]
Memory Maze is a 3D domain of randomized mazes designed for evaluating long-term memory in agents.
Unlike existing benchmarks, Memory Maze measures long-term memory separate from confounding agent abilities.
We find that current algorithms benefit from training with truncated backpropagation through time and succeed on small mazes, but fall short of human performance on the large mazes.
arXiv Detail & Related papers (2022-10-24T16:32:28Z) - Conceptual Design of the Memory System of the Robot Cognitive
Architecture ArmarX [6.201183690272094]
We describe conceptual and technical characteristics such a memory system has to fulfill, together with the underlying data representation.
We extend our robot software framework ArmarX into a unified cognitive architecture that is used in robots of the ARMAR humanoid robot family.
We show how the memory is used by the robots to implement memory-driven behaviors.
arXiv Detail & Related papers (2022-06-05T19:15:29Z) - CogNGen: Constructing the Kernel of a Hyperdimensional Predictive
Processing Cognitive Architecture [79.07468367923619]
We present a new cognitive architecture that combines two neurobiologically plausible, computational models.
We aim to develop a cognitive architecture that has the power of modern machine learning techniques.
arXiv Detail & Related papers (2022-03-31T04:44:28Z) - The Tensor Brain: A Unified Theory of Perception, Memory and Semantic
Decoding [16.37225919719441]
We present a unified computational theory of perception and memory.
In our model, perception, episodic memory, and semantic memory are realized by different functional and operational modes.
arXiv Detail & Related papers (2021-09-27T23:32:44Z) - Memory and attention in deep learning [19.70919701635945]
Memory construction for machine is inevitable.
Recent progresses on modeling memory in deep learning have revolved around external memory constructions.
The aim of this thesis is to advance the understanding on memory and attention in deep learning.
arXiv Detail & Related papers (2021-07-03T09:21:13Z) - Learning to Learn Variational Semantic Memory [132.39737669936125]
We introduce variational semantic memory into meta-learning to acquire long-term knowledge for few-shot learning.
The semantic memory is grown from scratch and gradually consolidated by absorbing information from tasks it experiences.
We formulate memory recall as the variational inference of a latent memory variable from addressed contents.
arXiv Detail & Related papers (2020-10-20T15:05:26Z) - Towards a Neural Model for Serial Order in Frontal Cortex: a Brain
Theory from Memory Development to Higher-Level Cognition [53.816853325427424]
We propose that the immature prefrontal cortex (PFC) use its primary functionality of detecting hierarchical patterns in temporal signals.
Our hypothesis is that the PFC detects the hierarchical structure in temporal sequences in the form of ordinal patterns and use them to index information hierarchically in different parts of the brain.
By doing so, it gives the tools to the language-ready brain for manipulating abstract knowledge and planning temporally ordered information.
arXiv Detail & Related papers (2020-05-22T14:29:51Z) - A Proposal for Intelligent Agents with Episodic Memory [0.9236074230806579]
We argue that an agent would benefit from an episodic memory.
This memory encodes the agent's experience in such a way that the agent can relive the experience.
We propose an architecture combining ANNs and standard Computer Science techniques for supporting storage and retrieval of episodic memories.
arXiv Detail & Related papers (2020-05-07T00:26:42Z) - Self-Attentive Associative Memory [69.40038844695917]
We propose to separate the storage of individual experiences (item memory) and their occurring relationships (relational memory)
We achieve competitive results with our proposed two-memory model in a diversity of machine learning tasks.
arXiv Detail & Related papers (2020-02-10T03:27:48Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.