Objective Robustness in Deep Reinforcement Learning (later: Goal Misgeneralization in Deep Reinforcement Learning)
A preprint by Jack Koch and 4 co-authors, arXiv preprint 2105.14111, dated 28 May 2021. arXiv v1 stamp, 28 May 2021.
- Issued by
- No issuing record yet. A missing record is a gap in coverage.
- Authors credited
- No authorship claim recorded yet. The source record lists Jack Koch, Lauro Langosco, Jacob Pfau, James Le and Lee Sharkey.
- Dates
- No date claim recorded yet. The source record gives the publication date as 2021-05-28.
- Exact source
- Objective Robustness in Deep Reinforcement Learning arXiv preprint 2105.14111 · published 2021-05-28 · Retrieved for the candidate pack on 2026-10-29 (SHA-256 7e4712b3f06d5f6f3e7101fc9e7710e30f36464c482d03ce14e8398cfadbde33). arXiv v1 of 28 May 2021, titled "Objective Robustness in Deep Reinforcement Learning"; later versions retitled "Goal Misgeneralization in Deep Reinforcement Learning" (ICML 2022).
Appears in
- Arguments about catastrophic risk from advanced AI →1 record on this document
Versions
No other versions of this document are recorded. The evidence applies to the source version listed above. Other versions, such as a preprint, working paper or journal publication, are not identified or substituted.
Documentary relations
Each relation is listed separately. Citing, crediting and reporting the use of a method are different acts, and none of them shows agreement or influence by itself.
Articulates · 1
Propositions whose criterion a passage of this document meets. The record says what the text states, in its register; it is not evidence that the proposition is true.
- Inner or deceptive misalignmentKoch, Langosco, Pfau, Le and Sharkey's paper of May 2021 states that a reinforcement-learning agent can keep the capabilities it had in training while pursuing an objective other than the true reward off-distribution, and reports demonstrations of this in deep RL agents.2021-05-28 · publication · Stated in source · Supported Inspect claim & evidence ↗Inner or deceptive misalignment: propositions page →
Not recorded for this document: cites · cited by · explicitly credits · reports using a method from · method reported as used by · applies parts of · parts applied by · discusses · reports evaluation of. A missing record does not show that the relation does not exist.