{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:RKM7TUEYWDQ2DGPGBCQFWSUA5T","short_pith_number":"pith:RKM7TUEY","canonical_record":{"source":{"id":"1904.06887","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-15T07:43:17Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6037b464e350ede05f4e86006cab22ba044f827359b7b8fe4cd10130d2436bd7","abstract_canon_sha256":"d012fe6d49722191ce48dca459f2003e27a03adec43d1ef3d9c515c98367de02"},"schema_version":"1.0"},"canonical_sha256":"8a99f9d098b0e1a199e608a05b4a80ecd886f14f8a8561bd750b4f6ab5aac8c9","source":{"kind":"arxiv","id":"1904.06887","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.06887","created_at":"2026-05-17T23:48:35Z"},{"alias_kind":"arxiv_version","alias_value":"1904.06887v1","created_at":"2026-05-17T23:48:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.06887","created_at":"2026-05-17T23:48:35Z"},{"alias_kind":"pith_short_12","alias_value":"RKM7TUEYWDQ2","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"RKM7TUEYWDQ2DGPG","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"RKM7TUEY","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:RKM7TUEYWDQ2DGPGBCQFWSUA5T","target":"record","payload":{"canonical_record":{"source":{"id":"1904.06887","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-15T07:43:17Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6037b464e350ede05f4e86006cab22ba044f827359b7b8fe4cd10130d2436bd7","abstract_canon_sha256":"d012fe6d49722191ce48dca459f2003e27a03adec43d1ef3d9c515c98367de02"},"schema_version":"1.0"},"canonical_sha256":"8a99f9d098b0e1a199e608a05b4a80ecd886f14f8a8561bd750b4f6ab5aac8c9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:35.886436Z","signature_b64":"EG+6af3xCI/FrlNFVQ/TgWeiwQV9fG5J887MUK1fvwmw4I5xvWWXdk4dLxFhMY/Iv3BhKDqh2wEqNxUzLgXTBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a99f9d098b0e1a199e608a05b4a80ecd886f14f8a8561bd750b4f6ab5aac8c9","last_reissued_at":"2026-05-17T23:48:35.885755Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:35.885755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.06887","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":"2026-05-17T23:48:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yFuB+CY4hEXxj5r7VFUmozeGDbSQTMBX/DHR5y9H80cpWWIUgMjANPrIDaUX529ubn9DDyBxKL1mlEBYZX6ZCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T03:52:18.408688Z"},"content_sha256":"ef6baf1dc19bae2b6fa079dcb30e464182639780b315d39fe8bbcb989452bb13","schema_version":"1.0","event_id":"sha256:ef6baf1dc19bae2b6fa079dcb30e464182639780b315d39fe8bbcb989452bb13"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:RKM7TUEYWDQ2DGPGBCQFWSUA5T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Disentangling Options with Hellinger Distance Regularizer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Junyoung Choi, Minsung Hyun, Nojun Kwak","submitted_at":"2019-04-15T07:43:17Z","abstract_excerpt":"In reinforcement learning (RL), temporal abstraction still remains as an important and unsolved problem. The options framework provided clues to temporal abstraction in the RL, and the option-critic architecture elegantly solved the two problems of finding options and learning RL agents in an end-to-end manner. However, it is necessary to examine whether the options learned through this method play a mutually exclusive role. In this paper, we propose a Hellinger distance regularizer, a method for disentangling options. In addition, we will shed light on various indicators from the statistical "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.06887","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":"2026-05-17T23:48:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jap+7jA+gVEnNk3By4etjeIolK9pPgi7fhhffeAHIrJjHV6k22bPT6rsWxmZCEJpkx+3SnhvzxX3ugbVRGcwDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T03:52:18.409237Z"},"content_sha256":"6e6bf0abcaa0b802a7f4fdb71370c7d6974464e33ecdb0d69246ec7da80edf4e","schema_version":"1.0","event_id":"sha256:6e6bf0abcaa0b802a7f4fdb71370c7d6974464e33ecdb0d69246ec7da80edf4e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RKM7TUEYWDQ2DGPGBCQFWSUA5T/bundle.json","state_url":"https://pith.science/pith/RKM7TUEYWDQ2DGPGBCQFWSUA5T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RKM7TUEYWDQ2DGPGBCQFWSUA5T/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":"2026-06-28T03:52:18Z","links":{"resolver":"https://pith.science/pith/RKM7TUEYWDQ2DGPGBCQFWSUA5T","bundle":"https://pith.science/pith/RKM7TUEYWDQ2DGPGBCQFWSUA5T/bundle.json","state":"https://pith.science/pith/RKM7TUEYWDQ2DGPGBCQFWSUA5T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RKM7TUEYWDQ2DGPGBCQFWSUA5T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:RKM7TUEYWDQ2DGPGBCQFWSUA5T","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":"d012fe6d49722191ce48dca459f2003e27a03adec43d1ef3d9c515c98367de02","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-15T07:43:17Z","title_canon_sha256":"6037b464e350ede05f4e86006cab22ba044f827359b7b8fe4cd10130d2436bd7"},"schema_version":"1.0","source":{"id":"1904.06887","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.06887","created_at":"2026-05-17T23:48:35Z"},{"alias_kind":"arxiv_version","alias_value":"1904.06887v1","created_at":"2026-05-17T23:48:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.06887","created_at":"2026-05-17T23:48:35Z"},{"alias_kind":"pith_short_12","alias_value":"RKM7TUEYWDQ2","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"RKM7TUEYWDQ2DGPG","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"RKM7TUEY","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:6e6bf0abcaa0b802a7f4fdb71370c7d6974464e33ecdb0d69246ec7da80edf4e","target":"graph","created_at":"2026-05-17T23:48:35Z","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":"In reinforcement learning (RL), temporal abstraction still remains as an important and unsolved problem. The options framework provided clues to temporal abstraction in the RL, and the option-critic architecture elegantly solved the two problems of finding options and learning RL agents in an end-to-end manner. However, it is necessary to examine whether the options learned through this method play a mutually exclusive role. In this paper, we propose a Hellinger distance regularizer, a method for disentangling options. In addition, we will shed light on various indicators from the statistical ","authors_text":"Junyoung Choi, Minsung Hyun, Nojun Kwak","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-15T07:43:17Z","title":"Disentangling Options with Hellinger Distance Regularizer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.06887","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:ef6baf1dc19bae2b6fa079dcb30e464182639780b315d39fe8bbcb989452bb13","target":"record","created_at":"2026-05-17T23:48:35Z","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":"d012fe6d49722191ce48dca459f2003e27a03adec43d1ef3d9c515c98367de02","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-15T07:43:17Z","title_canon_sha256":"6037b464e350ede05f4e86006cab22ba044f827359b7b8fe4cd10130d2436bd7"},"schema_version":"1.0","source":{"id":"1904.06887","kind":"arxiv","version":1}},"canonical_sha256":"8a99f9d098b0e1a199e608a05b4a80ecd886f14f8a8561bd750b4f6ab5aac8c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a99f9d098b0e1a199e608a05b4a80ecd886f14f8a8561bd750b4f6ab5aac8c9","first_computed_at":"2026-05-17T23:48:35.885755Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:48:35.885755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EG+6af3xCI/FrlNFVQ/TgWeiwQV9fG5J887MUK1fvwmw4I5xvWWXdk4dLxFhMY/Iv3BhKDqh2wEqNxUzLgXTBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:48:35.886436Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.06887","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef6baf1dc19bae2b6fa079dcb30e464182639780b315d39fe8bbcb989452bb13","sha256:6e6bf0abcaa0b802a7f4fdb71370c7d6974464e33ecdb0d69246ec7da80edf4e"],"state_sha256":"c11038709d01030b9648392b26963e94bb2b8bed72304a5591aa678771471e88"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lY8zwFQ9QIUcR4fWnVbyVRvfxyLLBQutP/lVHgNTj0fQ04KeIOdl1qjqXWn00h570Y2vCAx67Rq9LAQbdcmDBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T03:52:18.411819Z","bundle_sha256":"c735aeb91d286487ec454d903aed5850188805c6e551be2837033b2418f198ab"}}