Skip to content

tinker_cookbook.rl.ProblemGroupBuilder

class tinker_cookbook.rl.ProblemGroupBuilder(EnvGroupBuilder)

Builds a group of ProblemEnv instances from a factory callable.

Fields:

make_envs()

Create num_envs ProblemEnv instances using the factory callable.

Returns: Sequence[Env]

compute_group_rewards(trajectory_group, env_group)

Return zero group rewards (all rewards come from per-step scoring).

Parameters:

Returns: list[tuple[float, Metrics]]