{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:IRX5A53NHYR4QSPA6HTZUGBPWD","short_pith_number":"pith:IRX5A53N","canonical_record":{"source":{"id":"1806.05292","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-13T22:40:49Z","cross_cats_sorted":[],"title_canon_sha256":"7c7c3e23f26c9f3d0c567f951b48afcc96622847bd1b0421b77066a34f7338f3","abstract_canon_sha256":"11a1ce74e5cbb6341c192f836e26b763174c74f87f8ef7b67f8e222ef39c73de"},"schema_version":"1.0"},"canonical_sha256":"446fd0776d3e23c849e0f1e79a182fb0f1533a390df3fec8cbd60406ce03355a","source":{"kind":"arxiv","id":"1806.05292","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.05292","created_at":"2026-05-18T00:13:16Z"},{"alias_kind":"arxiv_version","alias_value":"1806.05292v1","created_at":"2026-05-18T00:13:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.05292","created_at":"2026-05-18T00:13:16Z"},{"alias_kind":"pith_short_12","alias_value":"IRX5A53NHYR4","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"IRX5A53NHYR4QSPA","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"IRX5A53N","created_at":"2026-05-18T12:32:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:IRX5A53NHYR4QSPA6HTZUGBPWD","target":"record","payload":{"canonical_record":{"source":{"id":"1806.05292","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-13T22:40:49Z","cross_cats_sorted":[],"title_canon_sha256":"7c7c3e23f26c9f3d0c567f951b48afcc96622847bd1b0421b77066a34f7338f3","abstract_canon_sha256":"11a1ce74e5cbb6341c192f836e26b763174c74f87f8ef7b67f8e222ef39c73de"},"schema_version":"1.0"},"canonical_sha256":"446fd0776d3e23c849e0f1e79a182fb0f1533a390df3fec8cbd60406ce03355a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:16.485451Z","signature_b64":"V8IdzfwXVPtWqHKHl5WsF+ixtudl8uxJPjgQgiLV8SfVz2GAu/nwR5j/H21kSdLjVSVa4mHIFPODP7gGalSFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"446fd0776d3e23c849e0f1e79a182fb0f1533a390df3fec8cbd60406ce03355a","last_reissued_at":"2026-05-18T00:13:16.484771Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:16.484771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.05292","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":"2026-05-18T00:13:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"afn3yLdKMRI0NPEYkKvJzQWhjlaU4ThQ+njy2PJJiYDmjKwr9aq8iJOuw7F2fKGcNC59nW80ZoQG2MXK0AduCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T02:44:34.599349Z"},"content_sha256":"2e07f9652be333d573c341aacb1470d3fe9f8615943911608cb9b2be7681b516","schema_version":"1.0","event_id":"sha256:2e07f9652be333d573c341aacb1470d3fe9f8615943911608cb9b2be7681b516"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:IRX5A53NHYR4QSPA6HTZUGBPWD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automatic formation of the structure of abstract machines in hierarchical reinforcement learning with state clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aleksandr I. Panov, Aleksey Skrynnik","submitted_at":"2018-06-13T22:40:49Z","abstract_excerpt":"We introduce a new approach to hierarchy formation and task decomposition in hierarchical reinforcement learning. Our method is based on the Hierarchy Of Abstract Machines (HAM) framework because HAM approach is able to design efficient controllers that will realize specific behaviors in real robots. The key to our algorithm is the introduction of the internal or \"mental\" environment in which the state represents the structure of the HAM hierarchy. The internal action in this environment leads to changes the hierarchy of HAMs. We propose the classical Q-learning procedure in the internal envir"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.05292","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":""},"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":"2026-05-18T00:13:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9r8boQ46rky7BFhAVUPf1t7dbck9v4QXRKzjYtBMb4Emyk917vBy2XfDrUkd9Hb3mPZC2koWEkNeHd/yHJt8CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T02:44:34.599687Z"},"content_sha256":"56b88eb493296091cb28d7477fb679ef94befd9ff2c0695b8b73c74206f243fb","schema_version":"1.0","event_id":"sha256:56b88eb493296091cb28d7477fb679ef94befd9ff2c0695b8b73c74206f243fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IRX5A53NHYR4QSPA6HTZUGBPWD/bundle.json","state_url":"https://pith.science/pith/IRX5A53NHYR4QSPA6HTZUGBPWD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IRX5A53NHYR4QSPA6HTZUGBPWD/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":"2026-06-28T02:44:34Z","links":{"resolver":"https://pith.science/pith/IRX5A53NHYR4QSPA6HTZUGBPWD","bundle":"https://pith.science/pith/IRX5A53NHYR4QSPA6HTZUGBPWD/bundle.json","state":"https://pith.science/pith/IRX5A53NHYR4QSPA6HTZUGBPWD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IRX5A53NHYR4QSPA6HTZUGBPWD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:IRX5A53NHYR4QSPA6HTZUGBPWD","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":"11a1ce74e5cbb6341c192f836e26b763174c74f87f8ef7b67f8e222ef39c73de","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-13T22:40:49Z","title_canon_sha256":"7c7c3e23f26c9f3d0c567f951b48afcc96622847bd1b0421b77066a34f7338f3"},"schema_version":"1.0","source":{"id":"1806.05292","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.05292","created_at":"2026-05-18T00:13:16Z"},{"alias_kind":"arxiv_version","alias_value":"1806.05292v1","created_at":"2026-05-18T00:13:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.05292","created_at":"2026-05-18T00:13:16Z"},{"alias_kind":"pith_short_12","alias_value":"IRX5A53NHYR4","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"IRX5A53NHYR4QSPA","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"IRX5A53N","created_at":"2026-05-18T12:32:31Z"}],"graph_snapshots":[{"event_id":"sha256:56b88eb493296091cb28d7477fb679ef94befd9ff2c0695b8b73c74206f243fb","target":"graph","created_at":"2026-05-18T00:13:16Z","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":"We introduce a new approach to hierarchy formation and task decomposition in hierarchical reinforcement learning. Our method is based on the Hierarchy Of Abstract Machines (HAM) framework because HAM approach is able to design efficient controllers that will realize specific behaviors in real robots. The key to our algorithm is the introduction of the internal or \"mental\" environment in which the state represents the structure of the HAM hierarchy. The internal action in this environment leads to changes the hierarchy of HAMs. We propose the classical Q-learning procedure in the internal envir","authors_text":"Aleksandr I. Panov, Aleksey Skrynnik","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-13T22:40:49Z","title":"Automatic formation of the structure of abstract machines in hierarchical reinforcement learning with state clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.05292","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":"sha256:2e07f9652be333d573c341aacb1470d3fe9f8615943911608cb9b2be7681b516","target":"record","created_at":"2026-05-18T00:13:16Z","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":"11a1ce74e5cbb6341c192f836e26b763174c74f87f8ef7b67f8e222ef39c73de","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-13T22:40:49Z","title_canon_sha256":"7c7c3e23f26c9f3d0c567f951b48afcc96622847bd1b0421b77066a34f7338f3"},"schema_version":"1.0","source":{"id":"1806.05292","kind":"arxiv","version":1}},"canonical_sha256":"446fd0776d3e23c849e0f1e79a182fb0f1533a390df3fec8cbd60406ce03355a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"446fd0776d3e23c849e0f1e79a182fb0f1533a390df3fec8cbd60406ce03355a","first_computed_at":"2026-05-18T00:13:16.484771Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:16.484771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V8IdzfwXVPtWqHKHl5WsF+ixtudl8uxJPjgQgiLV8SfVz2GAu/nwR5j/H21kSdLjVSVa4mHIFPODP7gGalSFAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:16.485451Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.05292","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e07f9652be333d573c341aacb1470d3fe9f8615943911608cb9b2be7681b516","sha256:56b88eb493296091cb28d7477fb679ef94befd9ff2c0695b8b73c74206f243fb"],"state_sha256":"c027f3f6aa68fe8497062dd4c7de54ade246812674f9e8a85221a58383d6b857"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"747zrGibmULMEFQtoV3mHUQHSzY8RM+nz6rrEh4zHgAA+bJZR0Bgkr1t5nDgXKAbRzPMUlgdBZBf2ZOARqc5DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T02:44:34.601506Z","bundle_sha256":"a9f926fd2c3ac3e58713b8d230df8b413c26cf84380000dd39de8214a9bacbde"}}