{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:64YOE2AJ4WWQQ5M7PQS4PKS3EK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fdb9caabfeeef24afecdbf8248774f0ee8dc68ee1fee985d775ac58b7fa00ccd","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-15T14:59:14Z","title_canon_sha256":"e31f8c23669b3e0431d488b11237f821c9bd5e68c8fba6c60248a866fad00443"},"schema_version":"1.0","source":{"id":"2106.08199","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.08199","created_at":"2026-07-05T06:36:19Z"},{"alias_kind":"arxiv_version","alias_value":"2106.08199v2","created_at":"2026-07-05T06:36:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.08199","created_at":"2026-07-05T06:36:19Z"},{"alias_kind":"pith_short_12","alias_value":"64YOE2AJ4WWQ","created_at":"2026-07-05T06:36:19Z"},{"alias_kind":"pith_short_16","alias_value":"64YOE2AJ4WWQQ5M7","created_at":"2026-07-05T06:36:19Z"},{"alias_kind":"pith_short_8","alias_value":"64YOE2AJ","created_at":"2026-07-05T06:36:19Z"}],"graph_snapshots":[{"event_id":"sha256:86340417dca5f71d474f7f93c9f5d208e6d237196c361932d3fbf1a334652ce1","target":"graph","created_at":"2026-07-05T06:36:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2106.08199/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many advances that have improved the robustness and efficiency of deep reinforcement learning (RL) algorithms can, in one way or another, be understood as introducing additional objectives or constraints in the policy optimization step. This includes ideas as far ranging as exploration bonuses, entropy regularization, and regularization toward teachers or data priors. Often, the task reward and auxiliary objectives are in conflict, and in this paper we argue that this makes it natural to treat these cases as instances of multi-objective (MO) optimization problems. We demonstrate how this persp","authors_text":"Abbas Abdolmaleki, Andras Gyorgy, Arunkumar Byravan, Bobak Shahriari, Csaba Szepesvari, Dhruva TB, Giulia Vezzani, Jost Tobias Springenberg, Konstantinos Bousmalis, Martin Riedmiller, Nicolas Heess, Raia Hadsell, Sandy H. Huang, Shruti Mishra","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-15T14:59:14Z","title":"On Multi-objective Policy Optimization as a Tool for Reinforcement Learning: Case Studies in Offline RL and Finetuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.08199","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c37692c2f10854d9ed68872dd66e02baaa197d21f063e7b7d5f0002817205433","target":"record","created_at":"2026-07-05T06:36:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"fdb9caabfeeef24afecdbf8248774f0ee8dc68ee1fee985d775ac58b7fa00ccd","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-15T14:59:14Z","title_canon_sha256":"e31f8c23669b3e0431d488b11237f821c9bd5e68c8fba6c60248a866fad00443"},"schema_version":"1.0","source":{"id":"2106.08199","kind":"arxiv","version":2}},"canonical_sha256":"f730e26809e5ad08759f7c25c7aa5b22bfc589a850735e57c638cf1bdd9ae82f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f730e26809e5ad08759f7c25c7aa5b22bfc589a850735e57c638cf1bdd9ae82f","first_computed_at":"2026-07-05T06:36:19.296070Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:36:19.296070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fJc78OnE4G44pIkFY9s72z2lGMm7H73PfHBVkt6LvtBOojeKWtvxFbsVoI5BYPi5W5rI08OfIb4Hv78kzqkKCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:36:19.296531Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.08199","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c37692c2f10854d9ed68872dd66e02baaa197d21f063e7b7d5f0002817205433","sha256:86340417dca5f71d474f7f93c9f5d208e6d237196c361932d3fbf1a334652ce1"],"state_sha256":"9f348b450a7b081843d861ab3cf957d8e9d86fd3dbab6588509232d44bfe9201"}