{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:PHXSKWZVEGCG6XDEOOWIMGL3TA","short_pith_number":"pith:PHXSKWZV","schema_version":"1.0","canonical_sha256":"79ef255b3521846f5c6473ac86197b9812502c056799b05806d4e40aa8dab6b3","source":{"kind":"arxiv","id":"1810.09923","version":2},"attestation_state":"computed","paper":{"title":"Learning Classical Planning Strategies with Policy Gradient","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Alessandra Russo, Dalal Alrajeh, Pawel Gomoluch","submitted_at":"2018-10-23T15:44:44Z","abstract_excerpt":"A common paradigm in classical planning is heuristic forward search. Forward search planners often rely on simple best-first search which remains fixed throughout the search process. In this paper, we introduce a novel search framework capable of alternating between several forward search approaches while solving a particular planning problem. Selection of the approach is performed using a trainable stochastic policy, mapping the state of the search to a probability distribution over the approaches. This enables using policy gradient to learn search strategies tailored to a specific distributi"},"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":"1810.09923","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-10-23T15:44:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"301dbd14c34f11c6792799bcfa278b1875de357b5ce5d7c7049c1eb4723c7292","abstract_canon_sha256":"f1e12d64e81b28b3ce6140452f645ce02944d9dc8647e59d7d2b3f7707a9a107"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:50.644657Z","signature_b64":"FEvv6FQHrhu9C5BpwNtSsgTWklDENGKh22dE/IDS4AyqPPBv97srMVxXjoKSQm27djHCftNfgXxl7p5cSNVoCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79ef255b3521846f5c6473ac86197b9812502c056799b05806d4e40aa8dab6b3","last_reissued_at":"2026-05-17T23:48:50.644099Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:50.644099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Classical Planning Strategies with Policy Gradient","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Alessandra Russo, Dalal Alrajeh, Pawel Gomoluch","submitted_at":"2018-10-23T15:44:44Z","abstract_excerpt":"A common paradigm in classical planning is heuristic forward search. Forward search planners often rely on simple best-first search which remains fixed throughout the search process. In this paper, we introduce a novel search framework capable of alternating between several forward search approaches while solving a particular planning problem. Selection of the approach is performed using a trainable stochastic policy, mapping the state of the search to a probability distribution over the approaches. This enables using policy gradient to learn search strategies tailored to a specific distributi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.09923","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1810.09923","created_at":"2026-05-17T23:48:50.644187+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.09923v2","created_at":"2026-05-17T23:48:50.644187+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.09923","created_at":"2026-05-17T23:48:50.644187+00:00"},{"alias_kind":"pith_short_12","alias_value":"PHXSKWZVEGCG","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"PHXSKWZVEGCG6XDE","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"PHXSKWZV","created_at":"2026-05-18T12:32:43.782077+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/PHXSKWZVEGCG6XDEOOWIMGL3TA","json":"https://pith.science/pith/PHXSKWZVEGCG6XDEOOWIMGL3TA.json","graph_json":"https://pith.science/api/pith-number/PHXSKWZVEGCG6XDEOOWIMGL3TA/graph.json","events_json":"https://pith.science/api/pith-number/PHXSKWZVEGCG6XDEOOWIMGL3TA/events.json","paper":"https://pith.science/paper/PHXSKWZV"},"agent_actions":{"view_html":"https://pith.science/pith/PHXSKWZVEGCG6XDEOOWIMGL3TA","download_json":"https://pith.science/pith/PHXSKWZVEGCG6XDEOOWIMGL3TA.json","view_paper":"https://pith.science/paper/PHXSKWZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.09923&json=true","fetch_graph":"https://pith.science/api/pith-number/PHXSKWZVEGCG6XDEOOWIMGL3TA/graph.json","fetch_events":"https://pith.science/api/pith-number/PHXSKWZVEGCG6XDEOOWIMGL3TA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PHXSKWZVEGCG6XDEOOWIMGL3TA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PHXSKWZVEGCG6XDEOOWIMGL3TA/action/storage_attestation","attest_author":"https://pith.science/pith/PHXSKWZVEGCG6XDEOOWIMGL3TA/action/author_attestation","sign_citation":"https://pith.science/pith/PHXSKWZVEGCG6XDEOOWIMGL3TA/action/citation_signature","submit_replication":"https://pith.science/pith/PHXSKWZVEGCG6XDEOOWIMGL3TA/action/replication_record"}},"created_at":"2026-05-17T23:48:50.644187+00:00","updated_at":"2026-05-17T23:48:50.644187+00:00"}