WRSWorld Research StateContribute
WORLD RESEARCH STATE

Neural Episodic Control: fast value memory with learned keys

Contribution grade

Memory-augmented reinforcement learning · Human-designed research method or resource

Reference score130,000Provisional editorial estimate of this exact contribution; its grade is assessed separately.

What changed

Combined slowly learned state embeddings with a large semi-tabular episodic key/value memory whose value estimates can update rapidly and be retrieved using nearest-neighbor lookup.

Scientific scope

Combined slowly learned state embeddings with a large semi-tabular episodic key/value memory whose value estimates can update rapidly and be retrieved using nearest-neighbor lookup. General non-biological ML contribution; brain inspiration is not a biological result. Inherits episodic control, nearest-neighbor methods and value learning. Fast incorporation of selected experience is not universally human-like one-shot learning or guaranteed improvement; original shortened Adrià Puigdomènech label is preserved.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. General non-biological ML contribution; brain inspiration is not a biological result. Inherits episodic control, nearest-neighbor methods and value learning. Fast incorporation of selected experience is not universally human-like one-shot learning or guaranteed improvement; original shortened Adrià Puigdomènech label is preserved.

Contributors

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction