{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IHY5HVOR7JFLYUDIHE6DURWQDQ","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":"ef756a4bcc38734b0fa214c1318bd79c40ebee16cfae2f4eb220f63cc5ffad1d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-20T14:51:10Z","title_canon_sha256":"9cef61abfaff38fac6c041342db2cf3b50da761d21585a0d09c98ef520b9d06e"},"schema_version":"1.0","source":{"id":"2303.11166","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.11166","created_at":"2026-07-05T05:52:40Z"},{"alias_kind":"arxiv_version","alias_value":"2303.11166v1","created_at":"2026-07-05T05:52:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.11166","created_at":"2026-07-05T05:52:40Z"},{"alias_kind":"pith_short_12","alias_value":"IHY5HVOR7JFL","created_at":"2026-07-05T05:52:40Z"},{"alias_kind":"pith_short_16","alias_value":"IHY5HVOR7JFLYUDI","created_at":"2026-07-05T05:52:40Z"},{"alias_kind":"pith_short_8","alias_value":"IHY5HVOR","created_at":"2026-07-05T05:52:40Z"}],"graph_snapshots":[{"event_id":"sha256:f41f7bec6577b5c59062473a184386b810f8a36ecf8f5895cd51a89e148ac6e9","target":"graph","created_at":"2026-07-05T05:52:40Z","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/2303.11166/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, graph-based planning algorithms have gained much attention to solve goal-conditioned reinforcement learning (RL) tasks: they provide a sequence of subgoals to reach the target-goal, and the agents learn to execute subgoal-conditioned policies. However, the sample-efficiency of such RL schemes still remains a challenge, particularly for long-horizon tasks. To address this issue, we present a simple yet effective self-imitation scheme which distills a subgoal-conditioned policy into the target-goal-conditioned policy. Our intuition here is that to reach a target-goal, an agent should p","authors_text":"Jinwoo Shin, Junsu Kim, Kyunghwan Son, Sungsoo Ahn, Younggyo Seo","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-20T14:51:10Z","title":"Imitating Graph-Based Planning with Goal-Conditioned Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.11166","kind":"arxiv","version":1},"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":"sha256:88395152c3a156088cda483ae277a4f0a57c837d77434106e1953613b20ca3e2","target":"record","created_at":"2026-07-05T05:52:40Z","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":"ef756a4bcc38734b0fa214c1318bd79c40ebee16cfae2f4eb220f63cc5ffad1d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-20T14:51:10Z","title_canon_sha256":"9cef61abfaff38fac6c041342db2cf3b50da761d21585a0d09c98ef520b9d06e"},"schema_version":"1.0","source":{"id":"2303.11166","kind":"arxiv","version":1}},"canonical_sha256":"41f1d3d5d1fa4abc5068393c3a46d01c154a027a0b4080d7936420ef508745a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"41f1d3d5d1fa4abc5068393c3a46d01c154a027a0b4080d7936420ef508745a3","first_computed_at":"2026-07-05T05:52:40.992919Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:52:40.992919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ABygtKln5lyDpcdWvY852SYEUnBCs2eX3RvVJ7yMY6wBm7kbnYi/1a2ICqSWsenDWjhhrieyQMaO534ml5rvAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:52:40.993347Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.11166","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88395152c3a156088cda483ae277a4f0a57c837d77434106e1953613b20ca3e2","sha256:f41f7bec6577b5c59062473a184386b810f8a36ecf8f5895cd51a89e148ac6e9"],"state_sha256":"047a39bafe897927c2b49acc9414106e64631e94199b4b2cb77518ba3f4ba83f"}