{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ENT2BPQC233C2FOKIVDZEE5EHF","short_pith_number":"pith:ENT2BPQC","canonical_record":{"source":{"id":"1908.01478","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2019-08-05T05:59:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4a3a27a9c4cbb09e8c8d730d90134c9b05693c08abfb1ad5678a37dc26446144","abstract_canon_sha256":"4e9f5cef695bbb63f94e982c01dada354c8d43aca3eb568a4a556b79987ca7e7"},"schema_version":"1.0"},"canonical_sha256":"2367a0be02d6f62d15ca45479213a439499d0c0e8f905348d8934fe200381681","source":{"kind":"arxiv","id":"1908.01478","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.01478","created_at":"2026-07-05T04:18:26Z"},{"alias_kind":"arxiv_version","alias_value":"1908.01478v3","created_at":"2026-07-05T04:18:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.01478","created_at":"2026-07-05T04:18:26Z"},{"alias_kind":"pith_short_12","alias_value":"ENT2BPQC233C","created_at":"2026-07-05T04:18:26Z"},{"alias_kind":"pith_short_16","alias_value":"ENT2BPQC233C2FOK","created_at":"2026-07-05T04:18:26Z"},{"alias_kind":"pith_short_8","alias_value":"ENT2BPQC","created_at":"2026-07-05T04:18:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ENT2BPQC233C2FOKIVDZEE5EHF","target":"record","payload":{"canonical_record":{"source":{"id":"1908.01478","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2019-08-05T05:59:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4a3a27a9c4cbb09e8c8d730d90134c9b05693c08abfb1ad5678a37dc26446144","abstract_canon_sha256":"4e9f5cef695bbb63f94e982c01dada354c8d43aca3eb568a4a556b79987ca7e7"},"schema_version":"1.0"},"canonical_sha256":"2367a0be02d6f62d15ca45479213a439499d0c0e8f905348d8934fe200381681","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:18:26.005295Z","signature_b64":"May+vmhH1APYzoEU5/QdNnIPss56NzVL5lbhLxW0AyvzKQ9w6GyQeg4xWgR3bP1AVDDOfVmt44Gl6zokF73lBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2367a0be02d6f62d15ca45479213a439499d0c0e8f905348d8934fe200381681","last_reissued_at":"2026-07-05T04:18:26.004908Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:18:26.004908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.01478","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:18:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B5ppuHYp8rYj/kGMmwsSKkGjkup8+6qx8rwgfAA5y/jQgnAUOt/q+/q2QCucruEwiEPQlfmCMLAmjqfxt6rYAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T05:34:42.954701Z"},"content_sha256":"b8d5af1253f7af73bc029679791f03061921b2c9729065cc4f4b12d5fdef839b","schema_version":"1.0","event_id":"sha256:b8d5af1253f7af73bc029679791f03061921b2c9729065cc4f4b12d5fdef839b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ENT2BPQC233C2FOKIVDZEE5EHF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reusability and Transferability of Macro Actions for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.NE","authors_text":"Chun-Yi Lee, Henry Kuo, Kuan-Yu Chang, Yi-Hsiang Chang","submitted_at":"2019-08-05T05:59:40Z","abstract_excerpt":"Conventional reinforcement learning (RL) typically determines an appropriate primitive action at each timestep. However, by using a proper macro action, defined as a sequence of primitive actions, an agent is able to bypass intermediate states to a farther state and facilitate its learning procedure. The problem we would like to investigate is what associated beneficial properties that macro actions may possess. In this paper, we unveil the properties of reusability and transferability of macro actions. The first property, reusability, means that a macro action generated along with one RL meth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.01478","kind":"arxiv","version":3},"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/1908.01478/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":"2026-07-05T04:18:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EaxFEE70Xk7Nsvc1zoLVa6lMSulp0Y5OyuxdS2DYH3Sugny8P4BKxr6yOd1U1Hzl6RBHgDPWoCoVsFM3E5ieDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T05:34:42.955239Z"},"content_sha256":"2f4206e084d1a35d42d359e2baeb26e4496837ad128268b3d37c185ed33c01a0","schema_version":"1.0","event_id":"sha256:2f4206e084d1a35d42d359e2baeb26e4496837ad128268b3d37c185ed33c01a0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ENT2BPQC233C2FOKIVDZEE5EHF/bundle.json","state_url":"https://pith.science/pith/ENT2BPQC233C2FOKIVDZEE5EHF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ENT2BPQC233C2FOKIVDZEE5EHF/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":"2026-08-08T05:34:42Z","links":{"resolver":"https://pith.science/pith/ENT2BPQC233C2FOKIVDZEE5EHF","bundle":"https://pith.science/pith/ENT2BPQC233C2FOKIVDZEE5EHF/bundle.json","state":"https://pith.science/pith/ENT2BPQC233C2FOKIVDZEE5EHF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ENT2BPQC233C2FOKIVDZEE5EHF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ENT2BPQC233C2FOKIVDZEE5EHF","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":"4e9f5cef695bbb63f94e982c01dada354c8d43aca3eb568a4a556b79987ca7e7","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2019-08-05T05:59:40Z","title_canon_sha256":"4a3a27a9c4cbb09e8c8d730d90134c9b05693c08abfb1ad5678a37dc26446144"},"schema_version":"1.0","source":{"id":"1908.01478","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.01478","created_at":"2026-07-05T04:18:26Z"},{"alias_kind":"arxiv_version","alias_value":"1908.01478v3","created_at":"2026-07-05T04:18:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.01478","created_at":"2026-07-05T04:18:26Z"},{"alias_kind":"pith_short_12","alias_value":"ENT2BPQC233C","created_at":"2026-07-05T04:18:26Z"},{"alias_kind":"pith_short_16","alias_value":"ENT2BPQC233C2FOK","created_at":"2026-07-05T04:18:26Z"},{"alias_kind":"pith_short_8","alias_value":"ENT2BPQC","created_at":"2026-07-05T04:18:26Z"}],"graph_snapshots":[{"event_id":"sha256:2f4206e084d1a35d42d359e2baeb26e4496837ad128268b3d37c185ed33c01a0","target":"graph","created_at":"2026-07-05T04:18:26Z","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/1908.01478/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Conventional reinforcement learning (RL) typically determines an appropriate primitive action at each timestep. However, by using a proper macro action, defined as a sequence of primitive actions, an agent is able to bypass intermediate states to a farther state and facilitate its learning procedure. The problem we would like to investigate is what associated beneficial properties that macro actions may possess. In this paper, we unveil the properties of reusability and transferability of macro actions. The first property, reusability, means that a macro action generated along with one RL meth","authors_text":"Chun-Yi Lee, Henry Kuo, Kuan-Yu Chang, Yi-Hsiang Chang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2019-08-05T05:59:40Z","title":"Reusability and Transferability of Macro Actions for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.01478","kind":"arxiv","version":3},"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:b8d5af1253f7af73bc029679791f03061921b2c9729065cc4f4b12d5fdef839b","target":"record","created_at":"2026-07-05T04:18:26Z","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":"4e9f5cef695bbb63f94e982c01dada354c8d43aca3eb568a4a556b79987ca7e7","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2019-08-05T05:59:40Z","title_canon_sha256":"4a3a27a9c4cbb09e8c8d730d90134c9b05693c08abfb1ad5678a37dc26446144"},"schema_version":"1.0","source":{"id":"1908.01478","kind":"arxiv","version":3}},"canonical_sha256":"2367a0be02d6f62d15ca45479213a439499d0c0e8f905348d8934fe200381681","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2367a0be02d6f62d15ca45479213a439499d0c0e8f905348d8934fe200381681","first_computed_at":"2026-07-05T04:18:26.004908Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:18:26.004908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"May+vmhH1APYzoEU5/QdNnIPss56NzVL5lbhLxW0AyvzKQ9w6GyQeg4xWgR3bP1AVDDOfVmt44Gl6zokF73lBw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:18:26.005295Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.01478","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b8d5af1253f7af73bc029679791f03061921b2c9729065cc4f4b12d5fdef839b","sha256:2f4206e084d1a35d42d359e2baeb26e4496837ad128268b3d37c185ed33c01a0"],"state_sha256":"e3d6b336dfaca83e037c34ab689e911b6187406a68546311c16fa0e3365e7eb4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BU59VrMBY+fidnewViLeNQ/cmi6vdznyAK/rKE5OIMvssK+dXowivMMfy71CLbxtvWD+nzyq921hvricTpV5Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T05:34:42.959418Z","bundle_sha256":"d1c5a95aeb8a2ca79cdb194335b871205ac21667291f52185f93e5c483d8b3c6"}}