A policy assigns actions to any state.

like starting in this state and the policy says,

How many here favor the first policy the state should recognize traditional marriage only?

So we'll start at a start state, we'll apply the policy and let's say the policy tells us to move in this direction.

But there's a well defined expectation over any possible execution of the policy pi that is generic to each state and each policy pi.

Policy

Privacy Policy

Group Policy

Default Policy

Password Policy

Duplicate Policy

Default Policy

Site Policy

Java policy

JavaScript policy

Switching Policy

cpu policy

Bad policy

Send policy

Cache Policy

Overwrite Policy

Size Policy

Focus Policy

Vert. Policy

Vertical Policy

So each state, except for the absorbing states, we have to define an action to define a policy.

So there is this key benefit that is relevant to state policy makers in terms of economic development.

For each status, my value of the state is the expected sum of future discounted reward provided that I start in state S, then I execute policy pi.

Add Group Policy

Add User Policy

Sound Policy Server

New Cookie Policy

Change Cookie Policy

New Java Policy

Change Java Policy

New JavaScript Policy

Change JavaScript Policy

New Plugin Policy

Change Plugin Policy

Group expand policy

Offline Cache Policy

That's my policy.

That's my policy.

While I haven't reached the goal state quite yet as indicated by checking for the star in my policy table.

In state 1 2, it's policy is moving down and then following this path, which it learned, towards the goal.