{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QFRI2SRHMQ5KSOB6RK6U56WVCO","short_pith_number":"pith:QFRI2SRH","schema_version":"1.0","canonical_sha256":"81628d4a27643aa9383e8abd4efad513b2ce2358599803294b1332f988d0fb77","source":{"kind":"arxiv","id":"2308.09734","version":1},"attestation_state":"computed","paper":{"title":"A Robust Policy Bootstrapping Algorithm for Multi-objective Reinforcement Learning in Non-stationary Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Jiankun Hu, Kathryn Kasmarik, Sherif Abdelfattah","submitted_at":"2023-08-18T02:15:12Z","abstract_excerpt":"Multi-objective Markov decision processes are a special kind of multi-objective optimization problem that involves sequential decision making while satisfying the Markov property of stochastic processes. Multi-objective reinforcement learning methods address this problem by fusing the reinforcement learning paradigm with multi-objective optimization techniques. One major drawback of these methods is the lack of adaptability to non-stationary dynamics in the environment. This is because they adopt optimization procedures that assume stationarity to evolve a coverage set of policies that can sol"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2308.09734","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-18T02:15:12Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"7dde99baf60fea8bca733aa62e3789d5fd567be91278db951a52bd59610bb664","abstract_canon_sha256":"1c49e808ffb9d2e7c639b6d57a4f197c9256b5da41ea035b3045d686b8638021"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:45.978612Z","signature_b64":"30Dyaz5519+XluSCmwcSkwipaoPb0v9EmRc1u+6On5U/bgOvYURsv9hNPcyekoUHDDsrbUYdEGHrtomL8a56Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81628d4a27643aa9383e8abd4efad513b2ce2358599803294b1332f988d0fb77","last_reissued_at":"2026-07-05T06:42:45.978166Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:45.978166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Robust Policy Bootstrapping Algorithm for Multi-objective Reinforcement Learning in Non-stationary Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Jiankun Hu, Kathryn Kasmarik, Sherif Abdelfattah","submitted_at":"2023-08-18T02:15:12Z","abstract_excerpt":"Multi-objective Markov decision processes are a special kind of multi-objective optimization problem that involves sequential decision making while satisfying the Markov property of stochastic processes. Multi-objective reinforcement learning methods address this problem by fusing the reinforcement learning paradigm with multi-objective optimization techniques. One major drawback of these methods is the lack of adaptability to non-stationary dynamics in the environment. This is because they adopt optimization procedures that assume stationarity to evolve a coverage set of policies that can sol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.09734","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2308.09734/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2308.09734","created_at":"2026-07-05T06:42:45.978220+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.09734v1","created_at":"2026-07-05T06:42:45.978220+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.09734","created_at":"2026-07-05T06:42:45.978220+00:00"},{"alias_kind":"pith_short_12","alias_value":"QFRI2SRHMQ5K","created_at":"2026-07-05T06:42:45.978220+00:00"},{"alias_kind":"pith_short_16","alias_value":"QFRI2SRHMQ5KSOB6","created_at":"2026-07-05T06:42:45.978220+00:00"},{"alias_kind":"pith_short_8","alias_value":"QFRI2SRH","created_at":"2026-07-05T06:42:45.978220+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QFRI2SRHMQ5KSOB6RK6U56WVCO","json":"https://pith.science/pith/QFRI2SRHMQ5KSOB6RK6U56WVCO.json","graph_json":"https://pith.science/api/pith-number/QFRI2SRHMQ5KSOB6RK6U56WVCO/graph.json","events_json":"https://pith.science/api/pith-number/QFRI2SRHMQ5KSOB6RK6U56WVCO/events.json","paper":"https://pith.science/paper/QFRI2SRH"},"agent_actions":{"view_html":"https://pith.science/pith/QFRI2SRHMQ5KSOB6RK6U56WVCO","download_json":"https://pith.science/pith/QFRI2SRHMQ5KSOB6RK6U56WVCO.json","view_paper":"https://pith.science/paper/QFRI2SRH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.09734&json=true","fetch_graph":"https://pith.science/api/pith-number/QFRI2SRHMQ5KSOB6RK6U56WVCO/graph.json","fetch_events":"https://pith.science/api/pith-number/QFRI2SRHMQ5KSOB6RK6U56WVCO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QFRI2SRHMQ5KSOB6RK6U56WVCO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QFRI2SRHMQ5KSOB6RK6U56WVCO/action/storage_attestation","attest_author":"https://pith.science/pith/QFRI2SRHMQ5KSOB6RK6U56WVCO/action/author_attestation","sign_citation":"https://pith.science/pith/QFRI2SRHMQ5KSOB6RK6U56WVCO/action/citation_signature","submit_replication":"https://pith.science/pith/QFRI2SRHMQ5KSOB6RK6U56WVCO/action/replication_record"}},"created_at":"2026-07-05T06:42:45.978220+00:00","updated_at":"2026-07-05T06:42:45.978220+00:00"}