Interface ValidateRewardParameters

Parameters for the validate_reward method.

Validates a reinforcement tuning reward configuration against a sample response and example before creating a reinforcement tuning job.

interface ValidateRewardParameters {
    compositeRewardConfig?: CompositeReinforcementTuningRewardConfig;
    config?: ValidateRewardConfig;
    example: ReinforcementTuningExample;
    parent: string;
    sampleResponse: Content;
    singleRewardConfig?: SingleReinforcementTuningRewardConfig;
}

Properties

compositeRewardConfig? config? example parent sampleResponse singleRewardConfig?

Properties

OptionalcompositeRewardConfig

compositeRewardConfig?: CompositeReinforcementTuningRewardConfig

Composite reward function configuration for reinforcement tuning. Mutually exclusive with single_reward_config.

Optionalconfig

config?: ValidateRewardConfig

Optional parameters for the request.

example

example: ReinforcementTuningExample

Required. The example to validate the reward configuration.

parent

parent: string

Required. The resource name of the Location to validate the reward in, e.g. projects/{project}/locations/{location}.

sampleResponse

sampleResponse: Content

Required. The sample response for validating the reward configuration.

OptionalsingleRewardConfig

singleRewardConfig?: SingleReinforcementTuningRewardConfig

Single reward function configuration for reinforcement tuning. Mutually exclusive with composite_reward_config.

Settings

On This Page

Properties