{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EILILBS3RWCBSTZIW5NARX3UE4","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":"8579401f52ad08ab7cc65818e317359295933294297b29cc1f4be26b181ad6e4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-04T16:21:10Z","title_canon_sha256":"a5cd27fe2b9c7e4f54122a1de9f364541b9a3aca8da79e57194e8bbb5ff0d788"},"schema_version":"1.0","source":{"id":"2501.02330","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.02330","created_at":"2026-07-05T11:20:07Z"},{"alias_kind":"arxiv_version","alias_value":"2501.02330v3","created_at":"2026-07-05T11:20:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.02330","created_at":"2026-07-05T11:20:07Z"},{"alias_kind":"pith_short_12","alias_value":"EILILBS3RWCB","created_at":"2026-07-05T11:20:07Z"},{"alias_kind":"pith_short_16","alias_value":"EILILBS3RWCBSTZI","created_at":"2026-07-05T11:20:07Z"},{"alias_kind":"pith_short_8","alias_value":"EILILBS3","created_at":"2026-07-05T11:20:07Z"}],"graph_snapshots":[{"event_id":"sha256:6c7aa192991ae6607180a2a238048848ef5c4019a7def6d2247112636d72c325","target":"graph","created_at":"2026-07-05T11:20:07Z","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/2501.02330/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose a novel method for learning reward functions directly from offline demonstrations. Unlike traditional inverse reinforcement learning (IRL), our approach decouples the reward function from the learner's policy, eliminating the adversarial interaction typically required between the two. This results in a more stable and efficient training process. Our reward function, called \\textit{SR-Reward}, leverages successor representation (SR) to encode a state based on expected future states' visitation under the demonstration policy and transition dynamics. By utilizing the Bel","authors_text":"Gabriel Kalweit, Joschka Boedecker, Seyed Mahdi B. Azad, Zahra Padar","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-04T16:21:10Z","title":"SR-Reward: Taking The Path More Traveled"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.02330","kind":"arxiv","version":3},"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:ec62f7e182b6068aa2d39295ea454974287489887d420e1c70fd0824e77fb7ac","target":"record","created_at":"2026-07-05T11:20:07Z","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":"8579401f52ad08ab7cc65818e317359295933294297b29cc1f4be26b181ad6e4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-04T16:21:10Z","title_canon_sha256":"a5cd27fe2b9c7e4f54122a1de9f364541b9a3aca8da79e57194e8bbb5ff0d788"},"schema_version":"1.0","source":{"id":"2501.02330","kind":"arxiv","version":3}},"canonical_sha256":"221685865b8d84194f28b75a08df7427282d23c515f6a25cdbab07907c86de85","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"221685865b8d84194f28b75a08df7427282d23c515f6a25cdbab07907c86de85","first_computed_at":"2026-07-05T11:20:07.789884Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:07.789884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k2F6Ve94QREfoVqSTAMLp6iRdYi2OvHJFacGnEFgQ0gMhYfy755MSo/u7FZ0ynDnjbmu1Dr3NmqzhSjssEeFCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:07.790368Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.02330","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec62f7e182b6068aa2d39295ea454974287489887d420e1c70fd0824e77fb7ac","sha256:6c7aa192991ae6607180a2a238048848ef5c4019a7def6d2247112636d72c325"],"state_sha256":"55878aca436ef605cbb247bc857de89653835209dbc836e26213f7cc71c4891c"}