{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:FG7KS5VDRRNYDLP264EHIH4GWE","short_pith_number":"pith:FG7KS5VD","canonical_record":{"source":{"id":"1904.10729","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-24T10:24:35Z","cross_cats_sorted":[],"title_canon_sha256":"638082926bd3627a0f46b236373bfe1c1a6b364a2ac3ebf4c758ea8e0c89c6c7","abstract_canon_sha256":"1abf819a5c87fc0db2628104989ae215d417b275ee281a3fa837c54e8e1962d4"},"schema_version":"1.0"},"canonical_sha256":"29bea976a38c5b81adfaf708741f86b130d7fcdb7ca68bda40dc0a85819470cc","source":{"kind":"arxiv","id":"1904.10729","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.10729","created_at":"2026-05-17T23:41:00Z"},{"alias_kind":"arxiv_version","alias_value":"1904.10729v2","created_at":"2026-05-17T23:41:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.10729","created_at":"2026-05-17T23:41:00Z"},{"alias_kind":"pith_short_12","alias_value":"FG7KS5VDRRNY","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"FG7KS5VDRRNYDLP2","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"FG7KS5VD","created_at":"2026-05-18T12:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:FG7KS5VDRRNYDLP264EHIH4GWE","target":"record","payload":{"canonical_record":{"source":{"id":"1904.10729","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-24T10:24:35Z","cross_cats_sorted":[],"title_canon_sha256":"638082926bd3627a0f46b236373bfe1c1a6b364a2ac3ebf4c758ea8e0c89c6c7","abstract_canon_sha256":"1abf819a5c87fc0db2628104989ae215d417b275ee281a3fa837c54e8e1962d4"},"schema_version":"1.0"},"canonical_sha256":"29bea976a38c5b81adfaf708741f86b130d7fcdb7ca68bda40dc0a85819470cc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:00.713530Z","signature_b64":"2PVhEykTLYAL2RKdnzg/DzP/F5TV6Z90EBjuvD1DYQvnnReABgep0GC9QKV93Iv34K/Fnsyqp4kEaKXzfKDjAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29bea976a38c5b81adfaf708741f86b130d7fcdb7ca68bda40dc0a85819470cc","last_reissued_at":"2026-05-17T23:41:00.713021Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:00.713021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.10729","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":"2026-05-17T23:41:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1P7/B9H+7D71eV9HMfMwoq0RLOdP3usirkL10yneG4vVyAeTXTNfXxl1zDtNcSmnJUEg7vl2MXxAnwbE8tSADA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T01:45:21.828659Z"},"content_sha256":"3618c73309c399b55683e462b338f4071d477cf8499d3e570045f463b8a2855f","schema_version":"1.0","event_id":"sha256:3618c73309c399b55683e462b338f4071d477cf8499d3e570045f463b8a2855f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:FG7KS5VDRRNYDLP264EHIH4GWE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Logic Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Shan Luo, Zhengyao Jiang","submitted_at":"2019-04-24T10:24:35Z","abstract_excerpt":"Deep reinforcement learning (DRL) has achieved significant breakthroughs in various tasks. However, most DRL algorithms suffer a problem of generalizing the learned policy which makes the learning performance largely affected even by minor modifications of the training environment. Except that, the use of deep neural networks makes the learned policies hard to be interpretable. To address these two challenges, we propose a novel algorithm named Neural Logic Reinforcement Learning (NLRL) to represent the policies in reinforcement learning by first-order logic. NLRL is based on policy gradient m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.10729","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":"2026-05-17T23:41:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QLmvdA6BJg2QCAiUQQ2/zmmluPwCgQnXB5HqWPCnBHgsJ6SYtyiruf3OwWzswFH6NzvcPaYZSjfbvT0cYQzHCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T01:45:21.829252Z"},"content_sha256":"88ec22da7a4288e3aa54ccdb2c5353a7cde86ccfc091d6a7135f91d1283ffdb6","schema_version":"1.0","event_id":"sha256:88ec22da7a4288e3aa54ccdb2c5353a7cde86ccfc091d6a7135f91d1283ffdb6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FG7KS5VDRRNYDLP264EHIH4GWE/bundle.json","state_url":"https://pith.science/pith/FG7KS5VDRRNYDLP264EHIH4GWE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FG7KS5VDRRNYDLP264EHIH4GWE/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":"2026-06-04T01:45:21Z","links":{"resolver":"https://pith.science/pith/FG7KS5VDRRNYDLP264EHIH4GWE","bundle":"https://pith.science/pith/FG7KS5VDRRNYDLP264EHIH4GWE/bundle.json","state":"https://pith.science/pith/FG7KS5VDRRNYDLP264EHIH4GWE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FG7KS5VDRRNYDLP264EHIH4GWE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:FG7KS5VDRRNYDLP264EHIH4GWE","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":"1abf819a5c87fc0db2628104989ae215d417b275ee281a3fa837c54e8e1962d4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-24T10:24:35Z","title_canon_sha256":"638082926bd3627a0f46b236373bfe1c1a6b364a2ac3ebf4c758ea8e0c89c6c7"},"schema_version":"1.0","source":{"id":"1904.10729","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.10729","created_at":"2026-05-17T23:41:00Z"},{"alias_kind":"arxiv_version","alias_value":"1904.10729v2","created_at":"2026-05-17T23:41:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.10729","created_at":"2026-05-17T23:41:00Z"},{"alias_kind":"pith_short_12","alias_value":"FG7KS5VDRRNY","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"FG7KS5VDRRNYDLP2","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"FG7KS5VD","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:88ec22da7a4288e3aa54ccdb2c5353a7cde86ccfc091d6a7135f91d1283ffdb6","target":"graph","created_at":"2026-05-17T23:41:00Z","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":"Deep reinforcement learning (DRL) has achieved significant breakthroughs in various tasks. However, most DRL algorithms suffer a problem of generalizing the learned policy which makes the learning performance largely affected even by minor modifications of the training environment. Except that, the use of deep neural networks makes the learned policies hard to be interpretable. To address these two challenges, we propose a novel algorithm named Neural Logic Reinforcement Learning (NLRL) to represent the policies in reinforcement learning by first-order logic. NLRL is based on policy gradient m","authors_text":"Shan Luo, Zhengyao Jiang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-24T10:24:35Z","title":"Neural Logic Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.10729","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":"sha256:3618c73309c399b55683e462b338f4071d477cf8499d3e570045f463b8a2855f","target":"record","created_at":"2026-05-17T23:41:00Z","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":"1abf819a5c87fc0db2628104989ae215d417b275ee281a3fa837c54e8e1962d4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-24T10:24:35Z","title_canon_sha256":"638082926bd3627a0f46b236373bfe1c1a6b364a2ac3ebf4c758ea8e0c89c6c7"},"schema_version":"1.0","source":{"id":"1904.10729","kind":"arxiv","version":2}},"canonical_sha256":"29bea976a38c5b81adfaf708741f86b130d7fcdb7ca68bda40dc0a85819470cc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29bea976a38c5b81adfaf708741f86b130d7fcdb7ca68bda40dc0a85819470cc","first_computed_at":"2026-05-17T23:41:00.713021Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:00.713021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2PVhEykTLYAL2RKdnzg/DzP/F5TV6Z90EBjuvD1DYQvnnReABgep0GC9QKV93Iv34K/Fnsyqp4kEaKXzfKDjAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:00.713530Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.10729","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3618c73309c399b55683e462b338f4071d477cf8499d3e570045f463b8a2855f","sha256:88ec22da7a4288e3aa54ccdb2c5353a7cde86ccfc091d6a7135f91d1283ffdb6"],"state_sha256":"9fbb272d6d3544d0525f58eb773a06adaadd76af28b88fcb8c2496b0debe2ff8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jyjK2VLpP85/x/J1h26u9GLpf10DjTzyE53Nq4Za6ZcOdBnarmRD9xM7D+JhhLo4XN3LvJx+zru2f8OwM8jaAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T01:45:21.832379Z","bundle_sha256":"5683e7e7fedf602f02ef362349090c7cd2c98e10354d4602e2159516be693cd0"}}