`nemo_gym.reward_profile`#

Module Contents#

Classes#

`RewardProfileConfig`
`RewardProfiler`

Functions#

reward_profile

API#

class nemo_gym.reward_profile.RewardProfileConfig(/, **data: typing.Any)[source]#

Bases: nemo_gym.config_types.BaseNeMoGymCLIConfig

materialized_inputs_jsonl_fpath: str#: ‘Field(…)’

rollouts_jsonl_fpath: str#: ‘Field(…)’

class nemo_gym.reward_profile.RewardProfiler[source]#

histogram(data: pandas.Series) → Optional[wandb.Histogram][source]#

describe_dataframe(df: pandas.DataFrame) → pandas.DataFrame[source]#

calculate_metrics_single_df( grouped_df: pandas.core.groupby.generic.DataFrameGroupBy, ) → List[Dict[str, Any]][source]#

profile_from_data( rows: List[Dict[str, Any]], results: List[Dict[str, Any]], ) → Tuple[List[Dict[str, Any]], List[Dict[str, Any]]][source]#

prepare_for_serialization( metrics: List[Dict], ) → List[Dict][source]#: Non-destructively cleans metrics output by RewardProfiler for downstream serialization.

write_to_disk( group_level_metrics: List[Dict[str, Any]], agent_level_metrics: List[Dict[str, Any]], base_output_fpath: pathlib.Path, ) → Tuple[pathlib.Path, pathlib.Path][source]#

nemo_gym.reward_profile.reward_profile()[source]#