Elements of episodic memory: insights from artificial agents
Bibliographic record
Abstract
Many recent artificial intelligence (AI) systems take inspiration from biological episodic memory. Here, we ask how these 'episodic-inspired' AI systems might inform our understanding of biological episodic memory. We discuss work showing that these systems implement some key features of episodic memory while differing in important respects and appear to enjoy behavioural advantages in the domains of strategic decision-making, fast learning, navigation, exploration and acting over temporal distance. We propose that these systems could be used to evaluate competing theories of episodic memory's operations and function. However, further work is needed to validate them as models of episodic memory and isolate the contributions of their memory systems to their behaviour. More immediately, we propose that these systems have a role to play in directing episodic memory research by highlighting novel or neglected hypotheses as pursuit-worthy. In this vein, we propose that the evidence reviewed here highlights two pursuit-worthy hypotheses about episodic memory's function: that it plays a role in planning that is independent of future-oriented simulation, and that it is adaptive in virtue of its contributions to fast learning in novel, sparse-reward environments. This article is part of the theme issue 'Elements of episodic memory: lessons from 40 years of research'.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.004 |
| Scholarly communication | 0.002 | 0.004 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".