Markov Decision Process

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

All possible configurations an agent may encounter.

Set of all actions available to the agent.

Strategy mapping states to actions.

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

Routes inputs to subsets of parameters for scalable capacity.

Chooses which experts process each token.

Capabilities that appear only beyond certain model sizes.

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