def make(self):
env = ValueWrapper(
TimeLimit(
ToyVMEnv(self.slate_size),
max_episode_steps=self.max_episode_steps,
),
zero_augment,
)
if self.initial_seed:
env.seed(self.initial_seed)
return env
def make(self) -> gym.Env:
env_config = {
"slate_size": self.slate_size,
"seed": self.initial_seed,
"num_candidates": self.num_candidates,
"resample_documents": self.resample_documents,
}
if self.is_interest_exploration:
env = interest_exploration.create_environment(env_config)
return ValueWrapper(env, lambda user, doc: 0.0)
if self.single_selection:
env = interest_evolution.create_environment(env_config)
return ValueWrapper(env, dot_value_fn)
else:
env = create_multiclick_environment(env_config)
return ValueWrapper(env, multi_selection_value_fn)