Read the equation
Adds a bounded utility contribution and subtracts an error penalty. The utility term can move the state in either direction, while nonnegative error lowers it.
Its role in the build
Adds a bounded utility contribution and subtracts an error penalty.
Terms & definitions
| Term | Meaning in this source |
|---|---|
| x | current scalar family state |
| dx | change signal |
| d_x / dx_norm | normalized change signal |
| u / utility | utility input |
| e / err | error input |
| s / stab | stability input |
| φ | golden-ratio constant |
How it works
Read the displayed expression together with the surrounding source statement; it is retained as an expression rather than silently completed into an equality.
Substitute the source-defined variables or recorded values and follow the displayed arithmetic and indexing exactly.
Use this version’s variable definitions and update order. The same symbol may be assigned a different meaning in another build.
Assumptions & limits
Conditions
The surrounding implementation must define the input scales and any output clipping.
An action space and mapping from this scalar state to actions are still required for a complete policy.
Original context
Exact original notation
x + 0.15×softsign(u) - 0.05×err
Related builds
Sources & provenance
x + 0.15×softsign(u) - 0.05×err