allenai / allenai/ScienceWorld

Disallow new steps/actions if the isCompleted flag is set

Offen
#31 9 Kommentare 0 Reaktionen 0 zugewiesene Personen Auf GitHub ansehen
To be confirmed
Vorherrschende Sprache
Scala
Sterne
391
Forks
42
PR-Merge-Kennzahlen
Keine gemergten PRs in 30 T.

Beschreibung

Certain conditions set the isCompleted flag to be set -- for example, a negative score in the task, signifying task failure:

https://github.com/allenai/ScienceWorld/blob/10dd21a483aca06bbd591a5465353f719dfaffc3/scienceworld/scienceworld.py#L328

Right now we set the isCompleted flag to be true, but if an agent doesn't check for this, it's still possible for it to continue to send commands to the environment. There is a report that this might let the tasks be gamed (especially the forced-choice tasks), as the agent might be able to take steps that ultimately further increase the score. We should likely modify the step() code so that if the isCompleted flag is set, it disallows further steps to be processed, to prevent any issues with agents reporting erroneously high scores in the future.

Beitragsleitfaden

Für dieses Repository ist kein Beitragsleitfaden indexiert

Bewertung

Dieses Issue wurde noch nicht bewertet.

Neue Issues direkt in Ihr Postfach

Eine kurze Übersicht über anfängerfreundliche GitHub-Issues.