{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:2PZFR24BH5OMZQLH6UETXG4TJZ","short_pith_number":"pith:2PZFR24B","schema_version":"1.0","canonical_sha256":"d3f258eb813f5cccc167f5093b9b934e5a99ca1554768ec4b6ad904e29f1e61c","source":{"kind":"arxiv","id":"1710.11417","version":2},"attestation_state":"computed","paper":{"title":"TreeQN and ATreeC: Differentiable Tree-Structured Models for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","stat.ML"],"primary_cat":"cs.AI","authors_text":"Gregory Farquhar, Maximilian Igl, Shimon Whiteson, Tim Rockt\\\"aschel","submitted_at":"2017-10-31T11:54:35Z","abstract_excerpt":"Combining deep model-free reinforcement learning with on-line planning is a promising approach to building on the successes of deep RL. On-line planning with look-ahead trees has proven successful in environments where transition models are known a priori. However, in complex environments where transition models need to be learned from data, the deficiencies of learned models have limited their utility for planning. To address these challenges, we propose TreeQN, a differentiable, recursive, tree-structured model that serves as a drop-in replacement for any value function network in deep RL wi"},"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":"1710.11417","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-10-31T11:54:35Z","cross_cats_sorted":["cs.LG","cs.NE","stat.ML"],"title_canon_sha256":"55b6cad677e276bcf0691699ca2c8ec0dea317b92c6567b0a86edd89989be1a1","abstract_canon_sha256":"0e68877c92ee7d46ece16c8bd1e603ad19ce4fa56db4faf963d433e31c904c13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:21:45.984251Z","signature_b64":"iqFIuK22B6/3Q5Al67znYSdHJ4Nh0sVbqJFXRx2bA3IKrO5DH6hDsaW5OIIt9IWy2IWqA3MFkb/yxowNbU1+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3f258eb813f5cccc167f5093b9b934e5a99ca1554768ec4b6ad904e29f1e61c","last_reissued_at":"2026-05-18T00:21:45.983514Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:21:45.983514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TreeQN and ATreeC: Differentiable Tree-Structured Models for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","stat.ML"],"primary_cat":"cs.AI","authors_text":"Gregory Farquhar, Maximilian Igl, Shimon Whiteson, Tim Rockt\\\"aschel","submitted_at":"2017-10-31T11:54:35Z","abstract_excerpt":"Combining deep model-free reinforcement learning with on-line planning is a promising approach to building on the successes of deep RL. On-line planning with look-ahead trees has proven successful in environments where transition models are known a priori. However, in complex environments where transition models need to be learned from data, the deficiencies of learned models have limited their utility for planning. To address these challenges, we propose TreeQN, a differentiable, recursive, tree-structured model that serves as a drop-in replacement for any value function network in deep RL wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.11417","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":"1710.11417","created_at":"2026-05-18T00:21:45.983630+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.11417v2","created_at":"2026-05-18T00:21:45.983630+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.11417","created_at":"2026-05-18T00:21:45.983630+00:00"},{"alias_kind":"pith_short_12","alias_value":"2PZFR24BH5OM","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_16","alias_value":"2PZFR24BH5OMZQLH","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_8","alias_value":"2PZFR24B","created_at":"2026-05-18T12:30:55.937587+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.01820","citing_title":"Risks from Learned Optimization in Advanced Machine Learning Systems","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2PZFR24BH5OMZQLH6UETXG4TJZ","json":"https://pith.science/pith/2PZFR24BH5OMZQLH6UETXG4TJZ.json","graph_json":"https://pith.science/api/pith-number/2PZFR24BH5OMZQLH6UETXG4TJZ/graph.json","events_json":"https://pith.science/api/pith-number/2PZFR24BH5OMZQLH6UETXG4TJZ/events.json","paper":"https://pith.science/paper/2PZFR24B"},"agent_actions":{"view_html":"https://pith.science/pith/2PZFR24BH5OMZQLH6UETXG4TJZ","download_json":"https://pith.science/pith/2PZFR24BH5OMZQLH6UETXG4TJZ.json","view_paper":"https://pith.science/paper/2PZFR24B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.11417&json=true","fetch_graph":"https://pith.science/api/pith-number/2PZFR24BH5OMZQLH6UETXG4TJZ/graph.json","fetch_events":"https://pith.science/api/pith-number/2PZFR24BH5OMZQLH6UETXG4TJZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2PZFR24BH5OMZQLH6UETXG4TJZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2PZFR24BH5OMZQLH6UETXG4TJZ/action/storage_attestation","attest_author":"https://pith.science/pith/2PZFR24BH5OMZQLH6UETXG4TJZ/action/author_attestation","sign_citation":"https://pith.science/pith/2PZFR24BH5OMZQLH6UETXG4TJZ/action/citation_signature","submit_replication":"https://pith.science/pith/2PZFR24BH5OMZQLH6UETXG4TJZ/action/replication_record"}},"created_at":"2026-05-18T00:21:45.983630+00:00","updated_at":"2026-05-18T00:21:45.983630+00:00"}