{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:UBGH4DG6IO2RWKQHG3SVKDENZX","short_pith_number":"pith:UBGH4DG6","canonical_record":{"source":{"id":"2106.11417","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-21T21:30:08Z","cross_cats_sorted":[],"title_canon_sha256":"d81cfaac49e9d541c232070f6e9d0cbc5586ddf9fd08f8c69f9f5788f1abca32","abstract_canon_sha256":"33e64f577d7c32856fc7533646d499477be72caa515187e4c837a30a4621b0c1"},"schema_version":"1.0"},"canonical_sha256":"a04c7e0cde43b51b2a0736e5550c8dcddfbb653d2c1f6f8f319be980224ab8a5","source":{"kind":"arxiv","id":"2106.11417","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.11417","created_at":"2026-07-05T02:51:29Z"},{"alias_kind":"arxiv_version","alias_value":"2106.11417v1","created_at":"2026-07-05T02:51:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.11417","created_at":"2026-07-05T02:51:29Z"},{"alias_kind":"pith_short_12","alias_value":"UBGH4DG6IO2R","created_at":"2026-07-05T02:51:29Z"},{"alias_kind":"pith_short_16","alias_value":"UBGH4DG6IO2RWKQH","created_at":"2026-07-05T02:51:29Z"},{"alias_kind":"pith_short_8","alias_value":"UBGH4DG6","created_at":"2026-07-05T02:51:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:UBGH4DG6IO2RWKQHG3SVKDENZX","target":"record","payload":{"canonical_record":{"source":{"id":"2106.11417","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-21T21:30:08Z","cross_cats_sorted":[],"title_canon_sha256":"d81cfaac49e9d541c232070f6e9d0cbc5586ddf9fd08f8c69f9f5788f1abca32","abstract_canon_sha256":"33e64f577d7c32856fc7533646d499477be72caa515187e4c837a30a4621b0c1"},"schema_version":"1.0"},"canonical_sha256":"a04c7e0cde43b51b2a0736e5550c8dcddfbb653d2c1f6f8f319be980224ab8a5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:51:29.083466Z","signature_b64":"u0fuww1d48Gx/1oQ65IHcUAxl3wXElcJib6mPaoAQmoqWIDHHM4MSk9yMjlXXdzJuEsgKi+FZprpl9rpmlOFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a04c7e0cde43b51b2a0736e5550c8dcddfbb653d2c1f6f8f319be980224ab8a5","last_reissued_at":"2026-07-05T02:51:29.083048Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:51:29.083048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.11417","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:51:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"spmXIzdNCdoWc2rpDhju5WhKmzCW/UylzdP5m7EJghl2034Sbb9KPYa26pcorJ3NKP8QdEGlQcmbvrHNEncjCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:29:16.738707Z"},"content_sha256":"a65fc761166257b94691e3e5ef4c2da98581d6d9ad639af2f6310c74ea6d5a03","schema_version":"1.0","event_id":"sha256:a65fc761166257b94691e3e5ef4c2da98581d6d9ad639af2f6310c74ea6d5a03"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:UBGH4DG6IO2RWKQHG3SVKDENZX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Interpretable Model-based Hierarchical Reinforcement Learning using Inductive Logic Programming","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Duo Xu, Faramarz Fekri","submitted_at":"2021-06-21T21:30:08Z","abstract_excerpt":"Recently deep reinforcement learning has achieved tremendous success in wide ranges of applications. However, it notoriously lacks data-efficiency and interpretability. Data-efficiency is important as interacting with the environment is expensive. Further, interpretability can increase the transparency of the black-box-style deep RL models and hence gain trust from the users. In this work, we propose a new hierarchical framework via symbolic RL, leveraging a symbolic transition model to improve the data-efficiency and introduce the interpretability for learned policy. This framework consists o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.11417","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2106.11417/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T02:51:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"je4MdSxqjnqK573P8p0GpItb0w9xz/PADptcUsDIbCIWlFulydd5rV4s5Iiiw47AM3JLYPJ/WsXjoHl2f/MYDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:29:16.739234Z"},"content_sha256":"b321f3300f564826ebc1d5b4b54d57ef47d3e9eda1c37f3d14af19a5cea9b7bd","schema_version":"1.0","event_id":"sha256:b321f3300f564826ebc1d5b4b54d57ef47d3e9eda1c37f3d14af19a5cea9b7bd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UBGH4DG6IO2RWKQHG3SVKDENZX/bundle.json","state_url":"https://pith.science/pith/UBGH4DG6IO2RWKQHG3SVKDENZX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UBGH4DG6IO2RWKQHG3SVKDENZX/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":"2026-08-08T15:29:16Z","links":{"resolver":"https://pith.science/pith/UBGH4DG6IO2RWKQHG3SVKDENZX","bundle":"https://pith.science/pith/UBGH4DG6IO2RWKQHG3SVKDENZX/bundle.json","state":"https://pith.science/pith/UBGH4DG6IO2RWKQHG3SVKDENZX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UBGH4DG6IO2RWKQHG3SVKDENZX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:UBGH4DG6IO2RWKQHG3SVKDENZX","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":"33e64f577d7c32856fc7533646d499477be72caa515187e4c837a30a4621b0c1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-21T21:30:08Z","title_canon_sha256":"d81cfaac49e9d541c232070f6e9d0cbc5586ddf9fd08f8c69f9f5788f1abca32"},"schema_version":"1.0","source":{"id":"2106.11417","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.11417","created_at":"2026-07-05T02:51:29Z"},{"alias_kind":"arxiv_version","alias_value":"2106.11417v1","created_at":"2026-07-05T02:51:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.11417","created_at":"2026-07-05T02:51:29Z"},{"alias_kind":"pith_short_12","alias_value":"UBGH4DG6IO2R","created_at":"2026-07-05T02:51:29Z"},{"alias_kind":"pith_short_16","alias_value":"UBGH4DG6IO2RWKQH","created_at":"2026-07-05T02:51:29Z"},{"alias_kind":"pith_short_8","alias_value":"UBGH4DG6","created_at":"2026-07-05T02:51:29Z"}],"graph_snapshots":[{"event_id":"sha256:b321f3300f564826ebc1d5b4b54d57ef47d3e9eda1c37f3d14af19a5cea9b7bd","target":"graph","created_at":"2026-07-05T02:51:29Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2106.11417/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently deep reinforcement learning has achieved tremendous success in wide ranges of applications. However, it notoriously lacks data-efficiency and interpretability. Data-efficiency is important as interacting with the environment is expensive. Further, interpretability can increase the transparency of the black-box-style deep RL models and hence gain trust from the users. In this work, we propose a new hierarchical framework via symbolic RL, leveraging a symbolic transition model to improve the data-efficiency and introduce the interpretability for learned policy. This framework consists o","authors_text":"Duo Xu, Faramarz Fekri","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-21T21:30:08Z","title":"Interpretable Model-based Hierarchical Reinforcement Learning using Inductive Logic Programming"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.11417","kind":"arxiv","version":1},"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:a65fc761166257b94691e3e5ef4c2da98581d6d9ad639af2f6310c74ea6d5a03","target":"record","created_at":"2026-07-05T02:51:29Z","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":"33e64f577d7c32856fc7533646d499477be72caa515187e4c837a30a4621b0c1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-21T21:30:08Z","title_canon_sha256":"d81cfaac49e9d541c232070f6e9d0cbc5586ddf9fd08f8c69f9f5788f1abca32"},"schema_version":"1.0","source":{"id":"2106.11417","kind":"arxiv","version":1}},"canonical_sha256":"a04c7e0cde43b51b2a0736e5550c8dcddfbb653d2c1f6f8f319be980224ab8a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a04c7e0cde43b51b2a0736e5550c8dcddfbb653d2c1f6f8f319be980224ab8a5","first_computed_at":"2026-07-05T02:51:29.083048Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:51:29.083048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u0fuww1d48Gx/1oQ65IHcUAxl3wXElcJib6mPaoAQmoqWIDHHM4MSk9yMjlXXdzJuEsgKi+FZprpl9rpmlOFAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:51:29.083466Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.11417","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a65fc761166257b94691e3e5ef4c2da98581d6d9ad639af2f6310c74ea6d5a03","sha256:b321f3300f564826ebc1d5b4b54d57ef47d3e9eda1c37f3d14af19a5cea9b7bd"],"state_sha256":"2c1fc7cad2e971ab4ade26af633eccd3de3e910a862182b7af09435f1b6de378"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oHS2rF5iMJFzwfHp+qpCJLS+1N15/xBzxPVGXKiXgQg2kk3HVCjYxdldVc3hothHAwVyaTLQDUB/tvzGW5eTAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T15:29:16.744879Z","bundle_sha256":"629a10ee451c429ec3b45044145dddbd90157b0e14e3a0bac98d52a652fdf8dc"}}