Skip to content

tinker_cookbook.rl.RolloutStrategy

class tinker_cookbook.rl.RolloutStrategy(ABC)

Controls how trajectories are collected from a group of environments.

property catches_group_errors

If True, group-level errors (make_envs, compute_group_rewards)

execute(env_group_builder, policy)

Create envs, run rollouts, and return results.

Parameters:

  • env_group_builder (EnvGroupBuilder) – Builder used to create the environments for this rollout group.
  • policy (TokenCompleter) – The policy (language model) used to generate actions during rollouts.

Returns: RolloutResult: The collected trajectories, surviving environments, and any errors encountered.