{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VRWAL5XZ5RXIEKTQHBOQGJLSU4","short_pith_number":"pith:VRWAL5XZ","schema_version":"1.0","canonical_sha256":"ac6c05f6f9ec6e822a70385d032572a73c05c8d12dc7cdb4a3220d0777ebfd34","source":{"kind":"arxiv","id":"2501.04228","version":2},"attestation_state":"computed","paper":{"title":"Constraints as Rewards: Reinforcement Learning for Robots without Reward Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Kazumi Aoyama, Kotaro Kawakami, Masaya Kinoshita, Noriaki Takasugi, Yu Ishihara","submitted_at":"2025-01-08T01:59:47Z","abstract_excerpt":"Reinforcement learning has become an essential algorithm for generating complex robotic behaviors. However, to learn such behaviors, it is necessary to design a reward function that describes the task, which often consists of multiple objectives that needs to be balanced. This tuning process is known as reward engineering and typically involves extensive trial-and-error. In this paper, to avoid this trial-and-error process, we propose the concept of Constraints as Rewards (CaR). CaR formulates the task objective using multiple constraint functions instead of a reward function and solves a rein"},"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":"2501.04228","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-01-08T01:59:47Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"703194a1086f778b7296eb1ec9acb3976fe02f7f23b9fd9a13ee7ea5492f4218","abstract_canon_sha256":"346d4933b64e4104be2661ec9f8bd67ca774fabcc522ffaef4646a16d9466cc5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:45.022334Z","signature_b64":"Rwdtcu/MTZ5bynCwA3jbJisnMXrKB+9v+0+tKlDpczoHsuXwXMk+qQp1yf8Ktqk3l5h1HvRb2NuCrC6azZT9DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac6c05f6f9ec6e822a70385d032572a73c05c8d12dc7cdb4a3220d0777ebfd34","last_reissued_at":"2026-07-05T09:58:45.021811Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:45.021811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Constraints as Rewards: Reinforcement Learning for Robots without Reward Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Kazumi Aoyama, Kotaro Kawakami, Masaya Kinoshita, Noriaki Takasugi, Yu Ishihara","submitted_at":"2025-01-08T01:59:47Z","abstract_excerpt":"Reinforcement learning has become an essential algorithm for generating complex robotic behaviors. However, to learn such behaviors, it is necessary to design a reward function that describes the task, which often consists of multiple objectives that needs to be balanced. This tuning process is known as reward engineering and typically involves extensive trial-and-error. In this paper, to avoid this trial-and-error process, we propose the concept of Constraints as Rewards (CaR). CaR formulates the task objective using multiple constraint functions instead of a reward function and solves a rein"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04228","kind":"arxiv","version":2},"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/2501.04228/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":"2501.04228","created_at":"2026-07-05T09:58:45.021869+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.04228v2","created_at":"2026-07-05T09:58:45.021869+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04228","created_at":"2026-07-05T09:58:45.021869+00:00"},{"alias_kind":"pith_short_12","alias_value":"VRWAL5XZ5RXI","created_at":"2026-07-05T09:58:45.021869+00:00"},{"alias_kind":"pith_short_16","alias_value":"VRWAL5XZ5RXIEKTQ","created_at":"2026-07-05T09:58:45.021869+00:00"},{"alias_kind":"pith_short_8","alias_value":"VRWAL5XZ","created_at":"2026-07-05T09:58:45.021869+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03177","citing_title":"ConTrack: Constrained Hand Motion Tracking with Adaptive Trade-off Control","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VRWAL5XZ5RXIEKTQHBOQGJLSU4","json":"https://pith.science/pith/VRWAL5XZ5RXIEKTQHBOQGJLSU4.json","graph_json":"https://pith.science/api/pith-number/VRWAL5XZ5RXIEKTQHBOQGJLSU4/graph.json","events_json":"https://pith.science/api/pith-number/VRWAL5XZ5RXIEKTQHBOQGJLSU4/events.json","paper":"https://pith.science/paper/VRWAL5XZ"},"agent_actions":{"view_html":"https://pith.science/pith/VRWAL5XZ5RXIEKTQHBOQGJLSU4","download_json":"https://pith.science/pith/VRWAL5XZ5RXIEKTQHBOQGJLSU4.json","view_paper":"https://pith.science/paper/VRWAL5XZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.04228&json=true","fetch_graph":"https://pith.science/api/pith-number/VRWAL5XZ5RXIEKTQHBOQGJLSU4/graph.json","fetch_events":"https://pith.science/api/pith-number/VRWAL5XZ5RXIEKTQHBOQGJLSU4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VRWAL5XZ5RXIEKTQHBOQGJLSU4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VRWAL5XZ5RXIEKTQHBOQGJLSU4/action/storage_attestation","attest_author":"https://pith.science/pith/VRWAL5XZ5RXIEKTQHBOQGJLSU4/action/author_attestation","sign_citation":"https://pith.science/pith/VRWAL5XZ5RXIEKTQHBOQGJLSU4/action/citation_signature","submit_replication":"https://pith.science/pith/VRWAL5XZ5RXIEKTQHBOQGJLSU4/action/replication_record"}},"created_at":"2026-07-05T09:58:45.021869+00:00","updated_at":"2026-07-05T09:58:45.021869+00:00"}