rlmesh::EpisodeResult
The outcome of one episode.
struct EpisodeResultFields
- index0-based episode index within the run.
- seedThe seed the episode was reset with, or
None. - stepsEnv steps taken.
- rewardTotal reward over the episode.
- terminatedWhether the env reported a terminal state.
- truncatedWhether the episode was cut short (env truncation, a cap, or the built-in step bound).
- successThe env-reported task outcome from the final step's info, or
None. - duration_sWall time from reset-return to episode end, in seconds.
- predict_msThe episode's mean per-step predict wall time, in milliseconds.
- step_msThe episode's mean per-step env-step wall time, in milliseconds.
- trialThe trial ordinal the episode walked, or
None.
index
field[source]index: i640-based episode index within the run.
seed
field[source]seed: Option<i64>The seed the episode was reset with, or None.
steps
field[source]steps: i64Env steps taken.
reward
field[source]reward: f64Total reward over the episode.
terminated
field[source]terminated: boolWhether the env reported a terminal state.
truncated
field[source]truncated: boolWhether the episode was cut short (env truncation, a cap, or the built-in step bound).
success
field[source]success: Option<bool>The env-reported task outcome from the final step’s info, or None.
duration_s
field[source]duration_s: f64Wall time from reset-return to episode end, in seconds.
predict_ms
field[source]predict_ms: Option<f64>The episode’s mean per-step predict wall time, in milliseconds.
step_ms
field[source]step_ms: Option<f64>The episode’s mean per-step env-step wall time, in milliseconds.
trial
field[source]trial: Option<i64>The trial ordinal the episode walked, or None.
Trait implementations
- impl Clone for EpisodeResult
- impl Debug for EpisodeResult
- impl Default for EpisodeResult
- impl StructuralPartialEq for EpisodeResult
- impl PartialEq for EpisodeResult
- impl Display for EpisodeResult