|dc.description.abstract||There are a variety of domains where it is desirable to learn a representation
of an environment defined by a stream of sensori-motor experience. This
dissertation introduces and formalizes subjective mapping, a novel approach to
this problem. A learned representation is subjective if it is constructed
almost entirely from the experience stream, minimizing the requirement of
additional domain-specific information (which is often not readily obtainable).
In many cases the observational data may be too plentiful to be feasibly stored.
In these cases, a primary feature of a learned representation is that it be
compact---summarizing information in a way that alleviates storage demands.
Consequently, the first key insight of the subjective mapping approach is to
phrase the problem as a variation of the well-studied problem of dimensionality
reduction. The second insight is that knowing the effects of actions is
critical to the usefulness of a representation. Therefore enforcing that
actions have a consistent and succinct form in the learned representation is
also a key requirement.
This dissertation presents a new framework, action respecting embedding (ARE),
which builds on a recent effective dimensionality reduction algorithm called
maximum variance unfolding, in order to solve the newly introduced subjective
mapping problem. The resulting learned representations are shown to be useful
for reasoning, planning and localization tasks. At the heart of the new
algorithm lies a semidefinite program leading to questions about ARE's ability
to handle sufficiently large input sizes. The final contribution of this
dissertation is to provide a divide-and-conquer algorithm as a first step to
addressing this issue.||en