Results for "excess return"

Returns above benchmark.

Optimizing policies directly via gradient ascent on expected reward.

Expected cumulative reward from a state or state-action pair.

Expected return of taking action in a state.

A learning paradigm where an agent interacts with an environment and learns to choose actions to maximize cumulative reward.

Strategy mapping states to actions.

Balancing learning new behaviors vs exploiting known rewards.

Centralized AI expertise group.

Formal framework for sequential decision-making under uncertainty.

Assigning AI costs to business units.

System returns to equilibrium after disturbance.

Stability proven via monotonic decrease of Lyapunov function.

Directly optimizing control policies.

Quantifying financial risk.

Learning only from current policy’s data.