Skip to content

tinker_cookbook.rl.TrajectoryGroup

class tinker_cookbook.rl.TrajectoryGroup(**)

A group of trajectories produced by one :class:EnvGroupBuilder.

Fields:

  • trajectories_G (list[Trajectory])
  • final_rewards_G (list[float]) – computed by the EnvGroupBuilder, looking at whole group
  • metrics_G (list[Metrics])
  • rollout_errors (list[RolloutError]) – Empty list means no trajectory errors occurred. Default: field(default_factory=list).

get_total_rewards()

Get the total reward (return) for each trajectory in the group.

Returns: list[float]: Total rewards, one per trajectory in the group.