Policy

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

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

Expected return of taking action in a state.

Fundamental recursive relationship defining optimal value functions.

Optimizing policies directly via gradient ascent on expected reward.

Empirical laws linking model size, data, compute to performance.

Formal framework for sequential decision-making under uncertainty.

All possible configurations an agent may encounter.

Set of all actions available to the agent.