{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IHY5HVOR7JFLYUDIHE6DURWQDQ","short_pith_number":"pith:IHY5HVOR","schema_version":"1.0","canonical_sha256":"41f1d3d5d1fa4abc5068393c3a46d01c154a027a0b4080d7936420ef508745a3","source":{"kind":"arxiv","id":"2303.11166","version":1},"attestation_state":"computed","paper":{"title":"Imitating Graph-Based Planning with Goal-Conditioned Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jinwoo Shin, Junsu Kim, Kyunghwan Son, Sungsoo Ahn, Younggyo Seo","submitted_at":"2023-03-20T14:51:10Z","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"},"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":"2303.11166","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-20T14:51:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9cef61abfaff38fac6c041342db2cf3b50da761d21585a0d09c98ef520b9d06e","abstract_canon_sha256":"ef756a4bcc38734b0fa214c1318bd79c40ebee16cfae2f4eb220f63cc5ffad1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:52:40.993347Z","signature_b64":"ABygtKln5lyDpcdWvY852SYEUnBCs2eX3RvVJ7yMY6wBm7kbnYi/1a2ICqSWsenDWjhhrieyQMaO534ml5rvAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41f1d3d5d1fa4abc5068393c3a46d01c154a027a0b4080d7936420ef508745a3","last_reissued_at":"2026-07-05T05:52:40.992919Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:52:40.992919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Imitating Graph-Based Planning with Goal-Conditioned Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jinwoo Shin, Junsu Kim, Kyunghwan Son, Sungsoo Ahn, Younggyo Seo","submitted_at":"2023-03-20T14:51:10Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.11166","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/2303.11166/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":"2303.11166","created_at":"2026-07-05T05:52:40.992976+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.11166v1","created_at":"2026-07-05T05:52:40.992976+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.11166","created_at":"2026-07-05T05:52:40.992976+00:00"},{"alias_kind":"pith_short_12","alias_value":"IHY5HVOR7JFL","created_at":"2026-07-05T05:52:40.992976+00:00"},{"alias_kind":"pith_short_16","alias_value":"IHY5HVOR7JFLYUDI","created_at":"2026-07-05T05:52:40.992976+00:00"},{"alias_kind":"pith_short_8","alias_value":"IHY5HVOR","created_at":"2026-07-05T05:52:40.992976+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.21039","citing_title":"Strict Subgoal Execution: Reliable Long-Horizon Planning in Hierarchical Reinforcement Learning","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IHY5HVOR7JFLYUDIHE6DURWQDQ","json":"https://pith.science/pith/IHY5HVOR7JFLYUDIHE6DURWQDQ.json","graph_json":"https://pith.science/api/pith-number/IHY5HVOR7JFLYUDIHE6DURWQDQ/graph.json","events_json":"https://pith.science/api/pith-number/IHY5HVOR7JFLYUDIHE6DURWQDQ/events.json","paper":"https://pith.science/paper/IHY5HVOR"},"agent_actions":{"view_html":"https://pith.science/pith/IHY5HVOR7JFLYUDIHE6DURWQDQ","download_json":"https://pith.science/pith/IHY5HVOR7JFLYUDIHE6DURWQDQ.json","view_paper":"https://pith.science/paper/IHY5HVOR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.11166&json=true","fetch_graph":"https://pith.science/api/pith-number/IHY5HVOR7JFLYUDIHE6DURWQDQ/graph.json","fetch_events":"https://pith.science/api/pith-number/IHY5HVOR7JFLYUDIHE6DURWQDQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IHY5HVOR7JFLYUDIHE6DURWQDQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IHY5HVOR7JFLYUDIHE6DURWQDQ/action/storage_attestation","attest_author":"https://pith.science/pith/IHY5HVOR7JFLYUDIHE6DURWQDQ/action/author_attestation","sign_citation":"https://pith.science/pith/IHY5HVOR7JFLYUDIHE6DURWQDQ/action/citation_signature","submit_replication":"https://pith.science/pith/IHY5HVOR7JFLYUDIHE6DURWQDQ/action/replication_record"}},"created_at":"2026-07-05T05:52:40.992976+00:00","updated_at":"2026-07-05T05:52:40.992976+00:00"}