{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:U4HQZ6G2GTKTKG47OUVAT7CN2Q","short_pith_number":"pith:U4HQZ6G2","canonical_record":{"source":{"id":"1811.00090","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-10-31T19:56:06Z","cross_cats_sorted":[],"title_canon_sha256":"3d6cb7b4325f1960b2a6db075d0e61c79fc7c4881c8b66fbce60d21fcd2eeb91","abstract_canon_sha256":"b27371f19cd832fecce8e9f4c014fe5a7e7733cb3e10bde739e1138645955b26"},"schema_version":"1.0"},"canonical_sha256":"a70f0cf8da34d5351b9f752a09fc4dd400170421968e2412e6ec638c5eddbabc","source":{"kind":"arxiv","id":"1811.00090","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.00090","created_at":"2026-05-17T23:52:27Z"},{"alias_kind":"arxiv_version","alias_value":"1811.00090v4","created_at":"2026-05-17T23:52:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.00090","created_at":"2026-05-17T23:52:27Z"},{"alias_kind":"pith_short_12","alias_value":"U4HQZ6G2GTKT","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"U4HQZ6G2GTKTKG47","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"U4HQZ6G2","created_at":"2026-05-18T12:32:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:U4HQZ6G2GTKTKG47OUVAT7CN2Q","target":"record","payload":{"canonical_record":{"source":{"id":"1811.00090","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-10-31T19:56:06Z","cross_cats_sorted":[],"title_canon_sha256":"3d6cb7b4325f1960b2a6db075d0e61c79fc7c4881c8b66fbce60d21fcd2eeb91","abstract_canon_sha256":"b27371f19cd832fecce8e9f4c014fe5a7e7733cb3e10bde739e1138645955b26"},"schema_version":"1.0"},"canonical_sha256":"a70f0cf8da34d5351b9f752a09fc4dd400170421968e2412e6ec638c5eddbabc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:27.017337Z","signature_b64":"OxsFzacTOsp8igx76C/aaiGEQ+/O7ND1BLrEGXJIbg1ydIIFVxkGIMArEYXjjI6WoW2/pbw7t/kWs76iz08oDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a70f0cf8da34d5351b9f752a09fc4dd400170421968e2412e6ec638c5eddbabc","last_reissued_at":"2026-05-17T23:52:27.016837Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:27.016837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.00090","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:52:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OtnxnY3k4sutYvMjoogk3rkcyKjErPps7JzjXGP01PkoqbD39OQlKrWmmX8bppHOR/K2BVjk3ZCZJU/AUsNWCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T06:38:12.971695Z"},"content_sha256":"299b48b63a9e15e42f7fd655d23630f0c77626733a0e8ec99437766e58b31c8e","schema_version":"1.0","event_id":"sha256:299b48b63a9e15e42f7fd655d23630f0c77626733a0e8ec99437766e58b31c8e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:U4HQZ6G2GTKTKG47OUVAT7CN2Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SDRL: Interpretable and Data-efficient Deep Reinforcement Learning Leveraging Symbolic Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bo Liu, Daoming Lyu, Fangkai Yang, Steven Gustafson","submitted_at":"2018-10-31T19:56:06Z","abstract_excerpt":"Deep reinforcement learning (DRL) has gained great success by learning directly from high-dimensional sensory inputs, yet is notorious for the lack of interpretability. Interpretability of the subtasks is critical in hierarchical decision-making as it increases the transparency of black-box-style DRL approach and helps the RL practitioners to understand the high-level behavior of the system better. In this paper, we introduce symbolic planning into DRL and propose a framework of Symbolic Deep Reinforcement Learning (SDRL) that can handle both high-dimensional sensory inputs and symbolic planni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.00090","kind":"arxiv","version":4},"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":"2026-05-17T23:52:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ybx4vR5FlWox8F8M5hTj9HJICEcNNv1HTWB6AGtO2Im7kd9QJgS+o7MpQ0yVA2FSmFJviylB5XjQwgNDyzHGDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T06:38:12.972465Z"},"content_sha256":"465b4d879225cefda6f737275ef673360b16ce327c9461927f13df33dcc732d8","schema_version":"1.0","event_id":"sha256:465b4d879225cefda6f737275ef673360b16ce327c9461927f13df33dcc732d8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U4HQZ6G2GTKTKG47OUVAT7CN2Q/bundle.json","state_url":"https://pith.science/pith/U4HQZ6G2GTKTKG47OUVAT7CN2Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U4HQZ6G2GTKTKG47OUVAT7CN2Q/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":"2026-06-01T06:38:12Z","links":{"resolver":"https://pith.science/pith/U4HQZ6G2GTKTKG47OUVAT7CN2Q","bundle":"https://pith.science/pith/U4HQZ6G2GTKTKG47OUVAT7CN2Q/bundle.json","state":"https://pith.science/pith/U4HQZ6G2GTKTKG47OUVAT7CN2Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U4HQZ6G2GTKTKG47OUVAT7CN2Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:U4HQZ6G2GTKTKG47OUVAT7CN2Q","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":"b27371f19cd832fecce8e9f4c014fe5a7e7733cb3e10bde739e1138645955b26","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-10-31T19:56:06Z","title_canon_sha256":"3d6cb7b4325f1960b2a6db075d0e61c79fc7c4881c8b66fbce60d21fcd2eeb91"},"schema_version":"1.0","source":{"id":"1811.00090","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.00090","created_at":"2026-05-17T23:52:27Z"},{"alias_kind":"arxiv_version","alias_value":"1811.00090v4","created_at":"2026-05-17T23:52:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.00090","created_at":"2026-05-17T23:52:27Z"},{"alias_kind":"pith_short_12","alias_value":"U4HQZ6G2GTKT","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"U4HQZ6G2GTKTKG47","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"U4HQZ6G2","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:465b4d879225cefda6f737275ef673360b16ce327c9461927f13df33dcc732d8","target":"graph","created_at":"2026-05-17T23:52:27Z","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 gained great success by learning directly from high-dimensional sensory inputs, yet is notorious for the lack of interpretability. Interpretability of the subtasks is critical in hierarchical decision-making as it increases the transparency of black-box-style DRL approach and helps the RL practitioners to understand the high-level behavior of the system better. In this paper, we introduce symbolic planning into DRL and propose a framework of Symbolic Deep Reinforcement Learning (SDRL) that can handle both high-dimensional sensory inputs and symbolic planni","authors_text":"Bo Liu, Daoming Lyu, Fangkai Yang, Steven Gustafson","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-10-31T19:56:06Z","title":"SDRL: Interpretable and Data-efficient Deep Reinforcement Learning Leveraging Symbolic Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.00090","kind":"arxiv","version":4},"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":"sha256:299b48b63a9e15e42f7fd655d23630f0c77626733a0e8ec99437766e58b31c8e","target":"record","created_at":"2026-05-17T23:52:27Z","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":"b27371f19cd832fecce8e9f4c014fe5a7e7733cb3e10bde739e1138645955b26","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-10-31T19:56:06Z","title_canon_sha256":"3d6cb7b4325f1960b2a6db075d0e61c79fc7c4881c8b66fbce60d21fcd2eeb91"},"schema_version":"1.0","source":{"id":"1811.00090","kind":"arxiv","version":4}},"canonical_sha256":"a70f0cf8da34d5351b9f752a09fc4dd400170421968e2412e6ec638c5eddbabc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a70f0cf8da34d5351b9f752a09fc4dd400170421968e2412e6ec638c5eddbabc","first_computed_at":"2026-05-17T23:52:27.016837Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:52:27.016837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OxsFzacTOsp8igx76C/aaiGEQ+/O7ND1BLrEGXJIbg1ydIIFVxkGIMArEYXjjI6WoW2/pbw7t/kWs76iz08oDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:52:27.017337Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.00090","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:299b48b63a9e15e42f7fd655d23630f0c77626733a0e8ec99437766e58b31c8e","sha256:465b4d879225cefda6f737275ef673360b16ce327c9461927f13df33dcc732d8"],"state_sha256":"beba81320630203c923df26ca44e25f1cf70ce1d2be4006569ea365d3e0fd551"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7meZNb2sOhZ7yESeJK+PSLvfGrT7tN3UHm3/pFHPKdGqViJfU57HqHvafN82ULpAMNHErJEw9P28U5olkh/9Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T06:38:12.975758Z","bundle_sha256":"5b904a5024375b82dc6050141e851cebc0393b953189fc383ed4821ef217acc4"}}