Construct · 2 fields · 4 citations

Where does policy collide?

One name. Different field. Different construct. One map.

● jingle · one word, two constructs Nearest construct by meaningreinforcementcompare the meanings
How to read this

Every construct on the map is compared with every other by the meaning of its definitions, and the closest one is surfaced here. The nearest construct to policy is reinforcement.

Hold this as a prompt, not a verdict. Two constructs sitting close in meaning is a reason to read them side by side and decide for yourself whether they are one idea under two names. It is not proof that they are. Compare the meanings in the Collider.

policy2 CONSTRUCTSPublic policyLASSWELL · POLICY PROCESSRL policyBELLMAN · DECISION RULE

Spokes are fields; dashed arcs are shared lineage. Tap a field for its definition, unit, and measures.

1951Public policy1957RL policy
2026

Drag to watch the word get claimed. Each field appears at the publication date of the earliest source cited for it. Tap a year to see which.

Political science and public administration

A government's course of action

In political science and public administration, policy is a government's chosen course of action or inaction on a public problem, together with the process by which it is decided and carried out. Harold Lasswell's 1951 The Policy Orientation founded the study of the policy sciences, and his 1956 The Decision Process laid out the stages through which a policy is framed, adopted, applied, and appraised. The referent is a public, collective commitment made through government, evidenced by statutes, budgets, and programs, and it is distinct from a private insurance contract or a rule mapping states to actions optimised by an algorithm.[1][2]

Unit
One government course of action on a public problem, from a statute or program to a deliberate choice not to act
Recovery means
Not applicable
Measured by
Traced through statutes, regulations, budgets, and program records, and appraised by their outcomes

Reinforcement learning and control

A mapping from states to actions

In reinforcement learning and control, a policy is a rule that maps each state an agent can be in to the action it should take there. Richard Bellman's 1957 Dynamic Programming introduced the term in its principle of optimality, which characterises an optimal policy for a sequence of decisions, and Sutton and Barto's 1998 Reinforcement Learning: An Introduction made it the central object of the field, where an agent learns a policy that maximises expected cumulative reward. The referent is a decision function inside a learning or control system, judged by the return it earns, and it has nothing to do with a government's course of action or an insurance contract beyond the shared word.[3][4]

Unit
One decision rule assigning an action to each state, either deterministic or a probability distribution over actions
Recovery means
Not applicable
Measured by
Evaluated by the expected cumulative reward (the return) it earns, estimated over sampled trajectories

Next

Run it through the Collider, or take the citations with you.

See how policy sits against neighbouring constructs in the Collider, or export every reference on this page in one click.

Open in ColliderExport BibTeXReport this collision

Nearby collisions

regulation4 fields · 4 citationsjingle · one word, four constructsagent3 fields · 5 citationsjingle · one word, three constructsgovernance4 fields · 5 citationsjingle · one word, four constructs

References

  1. Lasswell, H. D. (1951). The policy orientation. In D. Lerner & H. D. Lasswell (Eds.), The policy sciences (pp. 3–15). Stanford University Press.
  2. Lasswell, H. D. (1956). The decision process: Seven categories of functional analysis. University of Maryland Press.
  3. Bellman, R. (1957). Dynamic programming. Princeton University Press. ISBN 9780691079516
  4. Sutton, R. S., & Barto, A. G. (1998). Reinforcement learning: An introduction. MIT Press.

Cited on this page?

Confirm your construct, or correct us.

If your work is cited behind one of these entries, you know better than we do whether we captured the meaning right. Confirm it, suggest an edit, or dispute it, and your name goes on the entry as an author who has checked it, linked to your ORCID.

Claim your construct