{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:2PZFR24BH5OMZQLH6UETXG4TJZ","short_pith_number":"pith:2PZFR24B","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"},"canonical_sha256":"d3f258eb813f5cccc167f5093b9b934e5a99ca1554768ec4b6ad904e29f1e61c","source":{"kind":"arxiv","id":"1710.11417","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.11417","created_at":"2026-05-18T00:21:45Z"},{"alias_kind":"arxiv_version","alias_value":"1710.11417v2","created_at":"2026-05-18T00:21:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.11417","created_at":"2026-05-18T00:21:45Z"},{"alias_kind":"pith_short_12","alias_value":"2PZFR24BH5OM","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"2PZFR24BH5OMZQLH","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"2PZFR24B","created_at":"2026-05-18T12:30:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:2PZFR24BH5OMZQLH6UETXG4TJZ","target":"record","payload":{"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"},"canonical_sha256":"d3f258eb813f5cccc167f5093b9b934e5a99ca1554768ec4b6ad904e29f1e61c","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"},"source_kind":"arxiv","source_id":"1710.11417","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:21:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tmduIeAiBHGRBdt+vMogoNBjgNc8VsxGRqsPXb613oY5wC/0Bea18ZAyOGt6b46+Rq59fF2U0uqM63kR5J1DCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T22:32:08.903986Z"},"content_sha256":"e69787d47dc0fb993c6f108e7411c6c0279640513c487f0ad26c6ef244bf30c3","schema_version":"1.0","event_id":"sha256:e69787d47dc0fb993c6f108e7411c6c0279640513c487f0ad26c6ef244bf30c3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:2PZFR24BH5OMZQLH6UETXG4TJZ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:21:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g0bDghbFAUQ1/IXTlKPEqLcKhmpN1gGfTtTl3a3IYHnWQKr6eQuvVbYDJYMzjsT8iVhxkhAJiKwFBnDroI7qAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T22:32:08.904723Z"},"content_sha256":"3ddbe1a6d56cfc0439260c47c53f6468288d918116186e460ca0418a2bd8124a","schema_version":"1.0","event_id":"sha256:3ddbe1a6d56cfc0439260c47c53f6468288d918116186e460ca0418a2bd8124a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2PZFR24BH5OMZQLH6UETXG4TJZ/bundle.json","state_url":"https://pith.science/pith/2PZFR24BH5OMZQLH6UETXG4TJZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2PZFR24BH5OMZQLH6UETXG4TJZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-10T22:32:08Z","links":{"resolver":"https://pith.science/pith/2PZFR24BH5OMZQLH6UETXG4TJZ","bundle":"https://pith.science/pith/2PZFR24BH5OMZQLH6UETXG4TJZ/bundle.json","state":"https://pith.science/pith/2PZFR24BH5OMZQLH6UETXG4TJZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2PZFR24BH5OMZQLH6UETXG4TJZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:2PZFR24BH5OMZQLH6UETXG4TJZ","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":"0e68877c92ee7d46ece16c8bd1e603ad19ce4fa56db4faf963d433e31c904c13","cross_cats_sorted":["cs.LG","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-10-31T11:54:35Z","title_canon_sha256":"55b6cad677e276bcf0691699ca2c8ec0dea317b92c6567b0a86edd89989be1a1"},"schema_version":"1.0","source":{"id":"1710.11417","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.11417","created_at":"2026-05-18T00:21:45Z"},{"alias_kind":"arxiv_version","alias_value":"1710.11417v2","created_at":"2026-05-18T00:21:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.11417","created_at":"2026-05-18T00:21:45Z"},{"alias_kind":"pith_short_12","alias_value":"2PZFR24BH5OM","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"2PZFR24BH5OMZQLH","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"2PZFR24B","created_at":"2026-05-18T12:30:55Z"}],"graph_snapshots":[{"event_id":"sha256:3ddbe1a6d56cfc0439260c47c53f6468288d918116186e460ca0418a2bd8124a","target":"graph","created_at":"2026-05-18T00:21:45Z","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"},"paper":{"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","authors_text":"Gregory Farquhar, Maximilian Igl, Shimon Whiteson, Tim Rockt\\\"aschel","cross_cats":["cs.LG","cs.NE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-10-31T11:54:35Z","title":"TreeQN and ATreeC: Differentiable Tree-Structured Models for Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.11417","kind":"arxiv","version":2},"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:e69787d47dc0fb993c6f108e7411c6c0279640513c487f0ad26c6ef244bf30c3","target":"record","created_at":"2026-05-18T00:21:45Z","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":"0e68877c92ee7d46ece16c8bd1e603ad19ce4fa56db4faf963d433e31c904c13","cross_cats_sorted":["cs.LG","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-10-31T11:54:35Z","title_canon_sha256":"55b6cad677e276bcf0691699ca2c8ec0dea317b92c6567b0a86edd89989be1a1"},"schema_version":"1.0","source":{"id":"1710.11417","kind":"arxiv","version":2}},"canonical_sha256":"d3f258eb813f5cccc167f5093b9b934e5a99ca1554768ec4b6ad904e29f1e61c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d3f258eb813f5cccc167f5093b9b934e5a99ca1554768ec4b6ad904e29f1e61c","first_computed_at":"2026-05-18T00:21:45.983514Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:21:45.983514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iqFIuK22B6/3Q5Al67znYSdHJ4Nh0sVbqJFXRx2bA3IKrO5DH6hDsaW5OIIt9IWy2IWqA3MFkb/yxowNbU1+BQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:21:45.984251Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.11417","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e69787d47dc0fb993c6f108e7411c6c0279640513c487f0ad26c6ef244bf30c3","sha256:3ddbe1a6d56cfc0439260c47c53f6468288d918116186e460ca0418a2bd8124a"],"state_sha256":"639f85b42a6db20d74bbb8a4f41326408d84ade144925607f09b6eb31c7cc850"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xd2vQQVpcPlzYkY3dai/6pPxcdRLgc7IaQpE2l2a75BkVNNnSh22pHTDGNaCjNVpVRLGblcZxcdGCau2BUkYBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T22:32:08.908224Z","bundle_sha256":"1b50304c794c19008de73b7d9ad1150b545b31e785d4bd85d7629d6e091904bc"}}