{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/preprocessing-reward-functions-for","title":"Preprocessing Reward Functions for Interpretability","arxiv_id":"2203.13553","date":"2022-03-25","proceeding":null,"authors":["Erik Jenner","Adam Gleave"],"abstract":"In many real-world applications, the reward function is too complex to be manually specified. In such cases, reward functions must instead be learned from human feedback. Since the learned reward may fail to represent user preferences, it is important to be able to validate the learned reward function prior to deployment. One promising approach is to apply interpretability tools to the reward function to spot potential deviations from the user's intention. Existing work has applied general-purpose interpretability tools to understand learned reward functions. We propose exploiting the intrinsic structure of reward functions by first preprocessing them into simpler but equivalent reward functions, which are then visualized. We introduce a general framework for such reward preprocessing and propose concrete preprocessing algorithms. Our empirical evaluation shows that preprocessed rewards are often significantly easier to understand than the original reward.","url_abs":"https://arxiv.org/abs/2203.13553v1","url_pdf":"https://arxiv.org/pdf/2203.13553v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"preprocessing-reward-functions-for","repo_url":"https://github.com/humancompatibleai/reward-preprocessing","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.13553","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.13553"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/humancompatibleai/reward-preprocessing","reach":null}],"summary":{"ran_draft_wrong":1,"ran_fixture":1},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"fb9cfad937b0dbcd","entry":"log_abs","repo":"humancompatibleai/reward-preprocessing","repo_kind":"official","path":"src/reward_preprocessing/preprocess.py","file_url":"https://github.com/humancompatibleai/reward-preprocessing/blob/HEAD/src/reward_preprocessing/preprocess.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fb9cfad937b0dbcd"}},{"code_sha256_prefix":"13623ca117fd6838","entry":"smoothness","repo":"humancompatibleai/reward-preprocessing","repo_kind":"official","path":"src/reward_preprocessing/preprocess.py","file_url":"https://github.com/humancompatibleai/reward-preprocessing/blob/HEAD/src/reward_preprocessing/preprocess.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"13623ca117fd6838"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}