Mountain Car Case Study

Benchmark demonstrating that car position encodes as a 1D manifold; linear interventions fail by crossing voids; following the geometric curve produces smooth control.

Neighborhood — ranked by edge-count

Papers (1)

paper

The World Inside Neural Networks
mentions

Communities (1)

community

Neural Geometry
members_of

Findings (1)

finding

In the Mountain Car case study, car position is a 1D manifold; linear interventions cross voids causing incoherence; following the 1D curve produces smooth control.
citesimplements
Empirical demonstration that a semantically meaningful variable is encoded as a curved manifold, and that respecting its geometry is critical for effective intervention.

Concepts (1)

concept

Neural Geometries
associated_with

Related by similarity (3)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Mountain Car Problemconcept0.765
Engineering benchmark used to demonstrate active inference applicability
Mountain View Civic Centerconcept0.658
Unbuilt project in Mountain View, California, illustrating the differentiation of a building as a jewel in the street.
The car ... caused the loss of control and loss of belonging.claim0.651
Pinpoints the automobile as a primary agent in the destruction of public space and belonging