UPDATEREWARD()`¶

About UpdateReward¶

Updates the reward values for a trajectory and transitions it to reward-received status, signaling that it is eligible for processing. Call this operation after CompleteRollout to provide the computed reward scores.

Method Signature¶

METHODS /AWS1/IF_SGJ~UPDATEREWARD
  IMPORTING
    !IV_JOBARN TYPE /AWS1/SGJJOBARN OPTIONAL
    !IV_TRAJECTORYID TYPE /AWS1/SGJTRAJECTORYID OPTIONAL
    !IT_REWARDS TYPE /AWS1/CL_SGJDOUBLELIST_W=>TT_DOUBLELIST OPTIONAL
    !IV_CLIENTTOKEN TYPE /AWS1/SGJSTRING OPTIONAL
  RETURNING
    VALUE(OO_OUTPUT) TYPE REF TO /aws1/cl_sgjupdaterewardrsp
  RAISING
    /AWS1/CX_SGJACCESSDENIEDEX
    /AWS1/CX_SGJCONFLICTEXCEPTION
    /AWS1/CX_SGJINTSERVICEERROR
    /AWS1/CX_SGJRESOURCENOTFOUNDEX
    /AWS1/CX_SGJSERVICEQUOTAEXCDEX
    /AWS1/CX_SGJTHROTTLINGEX
    /AWS1/CX_SGJVLDTNEXCEPTION
    /AWS1/CX_SGJCLIENTEXC
    /AWS1/CX_SGJSERVEREXC
    /AWS1/CX_RT_TECHNICAL_GENERIC
    /AWS1/CX_RT_SERVICE_GENERIC.

IMPORTING¶

Required arguments:¶

`iv_jobarn` `TYPE /AWS1/SGJJOBARN` `/AWS1/SGJJOBARN`¶

The job ARN.

`iv_trajectoryid` `TYPE /AWS1/SGJTRAJECTORYID` `/AWS1/SGJTRAJECTORYID`¶

The trajectory ID to update with reward values.

`it_rewards` `TYPE /AWS1/CL_SGJDOUBLELIST_W=>TT_DOUBLELIST` `TT_DOUBLELIST`¶

The list of reward values to assign to this trajectory. Provide one reward value per turn in the trajectory.

Optional arguments:¶

`iv_clienttoken` `TYPE /AWS1/SGJSTRING` `/AWS1/SGJSTRING`¶

A unique, case-sensitive identifier that you provide to ensure the idempotency of the request.

RETURNING¶

`oo_output` `TYPE REF TO /aws1/cl_sgjupdaterewardrsp` `/AWS1/CL_SGJUPDATEREWARDRSP`¶

Examples¶

Syntax Example¶

This is an example of the syntax for calling the method. It includes every possible argument and initializes every possible value. The data provided is not necessarily semantically accurate (for example the value "string" may be provided for something that is intended to be an instance ID, or in some cases two arguments may be mutually exclusive). The syntax shows the ABAP syntax for creating the various data structures.

DATA(lo_result) = lo_client->updatereward(
  it_rewards = VALUE /aws1/cl_sgjdoublelist_w=>tt_doublelist(
    ( new /aws1/cl_sgjdoublelist_w( |0.1| ) )
  )
  iv_clienttoken = |string|
  iv_jobarn = |string|
  iv_trajectoryid = |string|
).

This is an example of reading all possible response values

lo_result = lo_result.
IF lo_result IS NOT INITIAL.
ENDIF.

Invoke UpdateReward¶

Updates the reward values for a completed trajectory.

DATA(lo_result) = lo_client->updatereward(
  it_rewards = VALUE /aws1/cl_sgjdoublelist_w=>tt_doublelist(
    ( new /aws1/cl_sgjdoublelist_w( |0.85| ) )
    ( new /aws1/cl_sgjdoublelist_w( |0.92| ) )
    ( new /aws1/cl_sgjdoublelist_w( |0.78| ) )
  )
  iv_jobarn = |arn:aws:sagemaker:us-east-1:123456789012:job/AgentRFT/my-training-job|
  iv_trajectoryid = |trajectory-001|
).

/AWS1/IF_SGJ=>UPDATEREWARD()¶