Results for "nonlinear function"

Variable whose values depend on chance.

Updated belief after observing data.

Approximating expectations via random sampling.

Restricting updates to safe regions.

Maximizing reward without fulfilling real goal.

Ensuring learned behavior matches intended objective.

Model behaves well during training but not deployment.

Willingness of system to accept correction or shutdown.

Asking model to review and improve output.

Applying learned patterns incorrectly.

Enables external computation or lookup.

Loss of old knowledge when learning new tasks.

Using output to adjust future inputs.

System returns to equilibrium after disturbance.

Predicts next state given current state and action.

Learning physical parameters from data.

Directly optimizing control policies.

Optimizing continuous action sequences.

Reward only given upon task completion.

Learning action mapping directly from demonstrations.

Sampling-based motion planner.

Optimal pathfinding algorithm.

Planning via artificial force fields.

Learning by minimizing prediction error.

Predicting protein 3D structure from sequence.

Predicting borrower default risk.

Agents optimize collective outcomes.

Tendency to gain control/resources.

Goals useful regardless of final objective.

Updating a pretrained model’s weights on task-specific data to improve performance or adapt style/behavior.