Emergent World Representations¶
Li, K., Hopkins, A. K., Bau, D., Viégas, F., Pfister, H., & Wattenberg, M. (2022). Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task. arXiv preprint.
Cited by¶
1 citation across 1 artifact.
Each citation links to the sentence it supports in the citing article.
Primes¶
- Good Regulator Theorem
- In AI and reinforcement learning, model-free agents seem to violate the theorem, but a successful policy network provably encodes predictive structure about its environment, and interpretability work on emergent world-models is the theorem instantiated in deep learning.
This sourceInterpretability evidence that a sequence model trained on Othello moves develops an internal representation of board state that causally controls its outputs — the good regulator theorem instantiated in deep learning.
- In AI and reinforcement learning, model-free agents seem to violate the theorem, but a successful policy network provably encodes predictive structure about its environment, and interpretability work on emergent world-models is the theorem instantiated in deep learning.
Verification¶
This reference passed the adversarial substantiation pipeline: it was checked to exist and to support the claim it is attached to. See how references were verified.
Registry ID ref:49b827ad2b63 · see in the full table