{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2APNLYBI7GE6OZINSWLBONKLEQ","short_pith_number":"pith:2APNLYBI","schema_version":"1.0","canonical_sha256":"d01ed5e028f989e7650d959617354b2422dea84709dbfde01f445edf788f31fa","source":{"kind":"arxiv","id":"2506.22008","version":1},"attestation_state":"computed","paper":{"title":"TROFI: Trajectory-Ranked Offline Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alessandro Sestini, Andrew D. Bagdanov, Joakim Bergdahl, Konrad Tollmar, Linus Gissl\\'en","submitted_at":"2025-06-27T08:22:41Z","abstract_excerpt":"In offline reinforcement learning, agents are trained using only a fixed set of stored transitions derived from a source policy. However, this requires that the dataset be labeled by a reward function. In applied settings such as video game development, the availability of the reward function is not always guaranteed. This paper proposes Trajectory-Ranked OFfline Inverse reinforcement learning (TROFI), a novel approach to effectively learn a policy offline without a pre-defined reward function. TROFI first learns a reward function from human preferences, which it then uses to label the origina"},"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":"2506.22008","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-27T08:22:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7b40aa3d081eac14e161521f74daaf1570e56a4ebade69253ecf163600a054f7","abstract_canon_sha256":"2c34feaf7a2a1ebfa0c1eb7a5732d57e5ae103e71f95aeaf32e6408a263db2e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:20.303020Z","signature_b64":"3ZjzzRFIDE0OJ+0FMKtO7Xmo4aOMiukoh3z63x8qbgUbBuHJMcHvbS3hGB76+KhvhEYb2xq+so/dMjxvcComCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d01ed5e028f989e7650d959617354b2422dea84709dbfde01f445edf788f31fa","last_reissued_at":"2026-07-05T11:28:20.302372Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:20.302372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TROFI: Trajectory-Ranked Offline Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alessandro Sestini, Andrew D. Bagdanov, Joakim Bergdahl, Konrad Tollmar, Linus Gissl\\'en","submitted_at":"2025-06-27T08:22:41Z","abstract_excerpt":"In offline reinforcement learning, agents are trained using only a fixed set of stored transitions derived from a source policy. However, this requires that the dataset be labeled by a reward function. In applied settings such as video game development, the availability of the reward function is not always guaranteed. This paper proposes Trajectory-Ranked OFfline Inverse reinforcement learning (TROFI), a novel approach to effectively learn a policy offline without a pre-defined reward function. TROFI first learns a reward function from human preferences, which it then uses to label the origina"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22008","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/2506.22008/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":"2506.22008","created_at":"2026-07-05T11:28:20.302436+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.22008v1","created_at":"2026-07-05T11:28:20.302436+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22008","created_at":"2026-07-05T11:28:20.302436+00:00"},{"alias_kind":"pith_short_12","alias_value":"2APNLYBI7GE6","created_at":"2026-07-05T11:28:20.302436+00:00"},{"alias_kind":"pith_short_16","alias_value":"2APNLYBI7GE6OZIN","created_at":"2026-07-05T11:28:20.302436+00:00"},{"alias_kind":"pith_short_8","alias_value":"2APNLYBI","created_at":"2026-07-05T11:28:20.302436+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/2APNLYBI7GE6OZINSWLBONKLEQ","json":"https://pith.science/pith/2APNLYBI7GE6OZINSWLBONKLEQ.json","graph_json":"https://pith.science/api/pith-number/2APNLYBI7GE6OZINSWLBONKLEQ/graph.json","events_json":"https://pith.science/api/pith-number/2APNLYBI7GE6OZINSWLBONKLEQ/events.json","paper":"https://pith.science/paper/2APNLYBI"},"agent_actions":{"view_html":"https://pith.science/pith/2APNLYBI7GE6OZINSWLBONKLEQ","download_json":"https://pith.science/pith/2APNLYBI7GE6OZINSWLBONKLEQ.json","view_paper":"https://pith.science/paper/2APNLYBI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.22008&json=true","fetch_graph":"https://pith.science/api/pith-number/2APNLYBI7GE6OZINSWLBONKLEQ/graph.json","fetch_events":"https://pith.science/api/pith-number/2APNLYBI7GE6OZINSWLBONKLEQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2APNLYBI7GE6OZINSWLBONKLEQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2APNLYBI7GE6OZINSWLBONKLEQ/action/storage_attestation","attest_author":"https://pith.science/pith/2APNLYBI7GE6OZINSWLBONKLEQ/action/author_attestation","sign_citation":"https://pith.science/pith/2APNLYBI7GE6OZINSWLBONKLEQ/action/citation_signature","submit_replication":"https://pith.science/pith/2APNLYBI7GE6OZINSWLBONKLEQ/action/replication_record"}},"created_at":"2026-07-05T11:28:20.302436+00:00","updated_at":"2026-07-05T11:28:20.302436+00:00"}