{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:IYYG3DEWRVRO4WBULNY3P7UYUV","short_pith_number":"pith:IYYG3DEW","schema_version":"1.0","canonical_sha256":"46306d8c968d62ee58345b71b7fe98a54066da4c932a942b1d906738446f8c0e","source":{"kind":"arxiv","id":"2006.02689","version":1},"attestation_state":"computed","paper":{"title":"Solving Hard AI Planning Instances Using Curriculum-Driven Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Bart Selman, Carla P. Gomes, Dieqiao Feng","submitted_at":"2020-06-04T08:13:12Z","abstract_excerpt":"Despite significant progress in general AI planning, certain domains remain out of reach of current AI planning systems. Sokoban is a PSPACE-complete planning task and represents one of the hardest domains for current AI planners. Even domain-specific specialized search methods fail quickly due to the exponential search complexity on hard instances. Our approach based on deep reinforcement learning augmented with a curriculum-driven method is the first one to solve hard instances within one day of training while other modern solvers cannot solve these instances within any reasonable time limit"},"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":"2006.02689","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-06-04T08:13:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"daf919eb9a5d569f1217202ea6014449f9230dd9ba3b52adcaf34cc3d1246cb2","abstract_canon_sha256":"5f035b1045d6131ab7d7103b834568e95bcde43341c9417868f69d84904fcc41"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:07:59.203526Z","signature_b64":"5TJf+rlxwDHC1FKFN/nIlakO+TKlK1hlYNDpiO+Y5QNX3zI+sDUVAGympZVodhJE9yCEJBn9ua0NtNxAxm0aCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46306d8c968d62ee58345b71b7fe98a54066da4c932a942b1d906738446f8c0e","last_reissued_at":"2026-07-05T01:07:59.203109Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:07:59.203109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Solving Hard AI Planning Instances Using Curriculum-Driven Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Bart Selman, Carla P. Gomes, Dieqiao Feng","submitted_at":"2020-06-04T08:13:12Z","abstract_excerpt":"Despite significant progress in general AI planning, certain domains remain out of reach of current AI planning systems. Sokoban is a PSPACE-complete planning task and represents one of the hardest domains for current AI planners. Even domain-specific specialized search methods fail quickly due to the exponential search complexity on hard instances. Our approach based on deep reinforcement learning augmented with a curriculum-driven method is the first one to solve hard instances within one day of training while other modern solvers cannot solve these instances within any reasonable time limit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.02689","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/2006.02689/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":"2006.02689","created_at":"2026-07-05T01:07:59.203169+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.02689v1","created_at":"2026-07-05T01:07:59.203169+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.02689","created_at":"2026-07-05T01:07:59.203169+00:00"},{"alias_kind":"pith_short_12","alias_value":"IYYG3DEWRVRO","created_at":"2026-07-05T01:07:59.203169+00:00"},{"alias_kind":"pith_short_16","alias_value":"IYYG3DEWRVRO4WBU","created_at":"2026-07-05T01:07:59.203169+00:00"},{"alias_kind":"pith_short_8","alias_value":"IYYG3DEW","created_at":"2026-07-05T01:07:59.203169+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03625","citing_title":"Self-Improvement for Fast, High-Quality Plan Generation","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IYYG3DEWRVRO4WBULNY3P7UYUV","json":"https://pith.science/pith/IYYG3DEWRVRO4WBULNY3P7UYUV.json","graph_json":"https://pith.science/api/pith-number/IYYG3DEWRVRO4WBULNY3P7UYUV/graph.json","events_json":"https://pith.science/api/pith-number/IYYG3DEWRVRO4WBULNY3P7UYUV/events.json","paper":"https://pith.science/paper/IYYG3DEW"},"agent_actions":{"view_html":"https://pith.science/pith/IYYG3DEWRVRO4WBULNY3P7UYUV","download_json":"https://pith.science/pith/IYYG3DEWRVRO4WBULNY3P7UYUV.json","view_paper":"https://pith.science/paper/IYYG3DEW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.02689&json=true","fetch_graph":"https://pith.science/api/pith-number/IYYG3DEWRVRO4WBULNY3P7UYUV/graph.json","fetch_events":"https://pith.science/api/pith-number/IYYG3DEWRVRO4WBULNY3P7UYUV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IYYG3DEWRVRO4WBULNY3P7UYUV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IYYG3DEWRVRO4WBULNY3P7UYUV/action/storage_attestation","attest_author":"https://pith.science/pith/IYYG3DEWRVRO4WBULNY3P7UYUV/action/author_attestation","sign_citation":"https://pith.science/pith/IYYG3DEWRVRO4WBULNY3P7UYUV/action/citation_signature","submit_replication":"https://pith.science/pith/IYYG3DEWRVRO4WBULNY3P7UYUV/action/replication_record"}},"created_at":"2026-07-05T01:07:59.203169+00:00","updated_at":"2026-07-05T01:07:59.203169+00:00"}