Autonomous agents that learn about their environment can be divided into two broad classes. One class of existing learners, reinforcement learners, typically employ weak learning ...
We introduce a simple variation of the additive heuristic used in the HSP planner that combines the benefits of the original additive heuristic, namely its mathematical formulation...
ys when planning meant searching for a sequence of abstract actions that satisfied some symbolic predicate. Robots can now learn their own representations through statistical infe...
This paper presents two object manipulation planning methods based on fitted stratified and semi-stratified approaches using finger relocations. The problem is discussed in the fr...
Most traditional approaches to probabilistic planning in relationally specified MDPs rely on grounding the problem w.r.t. specific domain instantiations, thereby incurring a com...