Results for "optimal solution"
Lowest possible loss.
Optimal control for linear systems with quadratic cost.
Alternative formulation providing bounds.
Fast approximation of costly simulations.
Fundamental recursive relationship defining optimal value functions.
Finding control policies minimizing cumulative cost.
Expected return of taking action in a state.
Training with a small labeled dataset plus a larger unlabeled dataset, leveraging assumptions like smoothness/cluster structure.
Distributed agents producing emergent intelligence.
Sensitivity of a function to input perturbations.
Restricting updates to safe regions.
Optimization under equality/inequality constraints.
Computing joint angles for desired end-effector pose.
Agents optimize collective outcomes.
Optimal estimator for linear dynamic systems.
Scaling law optimizing compute vs data.
Optimizing continuous action sequences.
Optimal pathfinding algorithm.
When a model cannot capture underlying structure, performing poorly on both training and test data.
Number of samples per gradient update; impacts compute efficiency, generalization, and stability.
One complete traversal of the training dataset during training.
Halting training when validation performance stops improving to reduce overfitting.
Tradeoffs between many layers vs many neurons per layer.
Set of all actions available to the agent.
Formal framework for sequential decision-making under uncertainty.
Strategy mapping states to actions.
Expected cumulative reward from a state or state-action pair.
Balancing learning new behaviors vs exploiting known rewards.
Number of steps considered in planning.
Visualization of optimization landscape.