def query_data(
self,
input_table_spec: TableSpec,
sample_range: Optional[Tuple[float, float]],
reward_options: RewardOptions,
data_fetcher: DataFetcher,
) -> Dataset:
return data_fetcher.query_data_synthetic_reward(
input_table_spec=input_table_spec,
discrete_action_names=self.model_manager.discrete_action_names,
sample_range=sample_range,
max_seq_len=self.model_manager.max_seq_len,
)
def query_data(
self,
input_table_spec: TableSpec,
sample_range: Optional[Tuple[float, float]],
reward_options: RewardOptions,
data_fetcher: DataFetcher,
) -> Dataset:
logger.info("Starting query")
return data_fetcher.query_data(
input_table_spec=input_table_spec,
discrete_action=False,
include_possible_actions=False,
custom_reward_expression=reward_options.custom_reward_expression,
sample_range=sample_range,
)
def query_data(
self,
input_table_spec: TableSpec,
sample_range: Optional[Tuple[float, float]],
reward_options: RewardOptions,
data_fetcher: DataFetcher,
) -> Dataset:
return data_fetcher.query_data(
input_table_spec=input_table_spec,
discrete_action=True,
actions=self.model_manager.action_names,
include_possible_actions=True,
sample_range=sample_range,
custom_reward_expression=reward_options.custom_reward_expression,
multi_steps=self.model_manager.multi_steps,
gamma=self.model_manager.rl_parameters.gamma,
)