{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:3T472DAFTCENHW2DY6FXFTBC7L","short_pith_number":"pith:3T472DAF","canonical_record":{"source":{"id":"1905.11222","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-05-23T21:27:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c399386b44dc73e6ccf9d5af935286c0bef01a91297f256b78f28d4add30d350","abstract_canon_sha256":"ab2fe89ebf172dd5698b29f44871bc616bf8ab21f65c59dc82f51250e64322fa"},"schema_version":"1.0"},"canonical_sha256":"dcf9fd0c059888d3db43c78b72cc22fae31a4d6539d9f8951f8c4cffef39573d","source":{"kind":"arxiv","id":"1905.11222","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.11222","created_at":"2026-05-17T23:43:32Z"},{"alias_kind":"arxiv_version","alias_value":"1905.11222v2","created_at":"2026-05-17T23:43:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11222","created_at":"2026-05-17T23:43:32Z"},{"alias_kind":"pith_short_12","alias_value":"3T472DAFTCEN","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"3T472DAFTCENHW2D","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"3T472DAF","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:3T472DAFTCENHW2DY6FXFTBC7L","target":"record","payload":{"canonical_record":{"source":{"id":"1905.11222","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-05-23T21:27:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c399386b44dc73e6ccf9d5af935286c0bef01a91297f256b78f28d4add30d350","abstract_canon_sha256":"ab2fe89ebf172dd5698b29f44871bc616bf8ab21f65c59dc82f51250e64322fa"},"schema_version":"1.0"},"canonical_sha256":"dcf9fd0c059888d3db43c78b72cc22fae31a4d6539d9f8951f8c4cffef39573d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:32.586077Z","signature_b64":"qRidKYAKZJ/khziLE2pfMgkANncfNnfr9TCcW2HqBy8bDGjfiXc9sVd3KhD1rWLWmjflepC9CxrHtyXucfF1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcf9fd0c059888d3db43c78b72cc22fae31a4d6539d9f8951f8c4cffef39573d","last_reissued_at":"2026-05-17T23:43:32.585675Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:32.585675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.11222","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:43:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8lm/niOzW1iC/kuD+5Fe7L4tS9iskHNLAA9dCI8tXWEvbfYcMC1yJhbcv4m23wk25eskUYhvK4Fy/8FoRWDJDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:40:17.137578Z"},"content_sha256":"b80d107f17742f51068e5121b647b485972385ddfca492d1e5560bf235ff24ac","schema_version":"1.0","event_id":"sha256:b80d107f17742f51068e5121b647b485972385ddfca492d1e5560bf235ff24ac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:3T472DAFTCENHW2DY6FXFTBC7L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Soft Options Critic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Elita Lobo, Scott Jordan","submitted_at":"2019-05-23T21:27:11Z","abstract_excerpt":"The option-critic architecture (Bacon, Harb, and Precup 2017) and several variants have successfully demonstrated the use of the options framework proposed by Sutton et al (Sutton, Precup, and Singh1999) to scale learning and planning in hierarchical tasks. Although most of these frameworks use entropy as a regularizer to improve exploration, they do not maximize entropy along with returns at every time step. (Haarnoja et al., 2018d) recently introduced an off-policy actor critic algorithm in theSoft Actor Critic paper that maximize returns while maximizing entropy in a constrained manner thus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11222","kind":"arxiv","version":2},"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":"2026-05-17T23:43:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rGeFFKFVgiVPREUa9JgEvt5Kk3oQM4cffVTRU8+isLSrr/vg74V94glCAMN9GEw/ohexgIrmPEk6/u5104GJAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:40:17.137986Z"},"content_sha256":"3f250f5b9743936ef031da347986cfa68c8145aaa3cd5c717385e9c4d3121e3b","schema_version":"1.0","event_id":"sha256:3f250f5b9743936ef031da347986cfa68c8145aaa3cd5c717385e9c4d3121e3b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3T472DAFTCENHW2DY6FXFTBC7L/bundle.json","state_url":"https://pith.science/pith/3T472DAFTCENHW2DY6FXFTBC7L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3T472DAFTCENHW2DY6FXFTBC7L/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":"2026-07-09T06:40:17Z","links":{"resolver":"https://pith.science/pith/3T472DAFTCENHW2DY6FXFTBC7L","bundle":"https://pith.science/pith/3T472DAFTCENHW2DY6FXFTBC7L/bundle.json","state":"https://pith.science/pith/3T472DAFTCENHW2DY6FXFTBC7L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3T472DAFTCENHW2DY6FXFTBC7L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:3T472DAFTCENHW2DY6FXFTBC7L","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":"ab2fe89ebf172dd5698b29f44871bc616bf8ab21f65c59dc82f51250e64322fa","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-05-23T21:27:11Z","title_canon_sha256":"c399386b44dc73e6ccf9d5af935286c0bef01a91297f256b78f28d4add30d350"},"schema_version":"1.0","source":{"id":"1905.11222","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.11222","created_at":"2026-05-17T23:43:32Z"},{"alias_kind":"arxiv_version","alias_value":"1905.11222v2","created_at":"2026-05-17T23:43:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11222","created_at":"2026-05-17T23:43:32Z"},{"alias_kind":"pith_short_12","alias_value":"3T472DAFTCEN","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"3T472DAFTCENHW2D","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"3T472DAF","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:3f250f5b9743936ef031da347986cfa68c8145aaa3cd5c717385e9c4d3121e3b","target":"graph","created_at":"2026-05-17T23:43:32Z","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":"The option-critic architecture (Bacon, Harb, and Precup 2017) and several variants have successfully demonstrated the use of the options framework proposed by Sutton et al (Sutton, Precup, and Singh1999) to scale learning and planning in hierarchical tasks. Although most of these frameworks use entropy as a regularizer to improve exploration, they do not maximize entropy along with returns at every time step. (Haarnoja et al., 2018d) recently introduced an off-policy actor critic algorithm in theSoft Actor Critic paper that maximize returns while maximizing entropy in a constrained manner thus","authors_text":"Elita Lobo, Scott Jordan","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-05-23T21:27:11Z","title":"Soft Options Critic"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11222","kind":"arxiv","version":2},"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:b80d107f17742f51068e5121b647b485972385ddfca492d1e5560bf235ff24ac","target":"record","created_at":"2026-05-17T23:43:32Z","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":"ab2fe89ebf172dd5698b29f44871bc616bf8ab21f65c59dc82f51250e64322fa","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-05-23T21:27:11Z","title_canon_sha256":"c399386b44dc73e6ccf9d5af935286c0bef01a91297f256b78f28d4add30d350"},"schema_version":"1.0","source":{"id":"1905.11222","kind":"arxiv","version":2}},"canonical_sha256":"dcf9fd0c059888d3db43c78b72cc22fae31a4d6539d9f8951f8c4cffef39573d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dcf9fd0c059888d3db43c78b72cc22fae31a4d6539d9f8951f8c4cffef39573d","first_computed_at":"2026-05-17T23:43:32.585675Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:32.585675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qRidKYAKZJ/khziLE2pfMgkANncfNnfr9TCcW2HqBy8bDGjfiXc9sVd3KhD1rWLWmjflepC9CxrHtyXucfF1DQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:32.586077Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.11222","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b80d107f17742f51068e5121b647b485972385ddfca492d1e5560bf235ff24ac","sha256:3f250f5b9743936ef031da347986cfa68c8145aaa3cd5c717385e9c4d3121e3b"],"state_sha256":"f881c4fdbe9b61a7c00bd28777b4a2dc2ec96d21764cb936b20dfb07d0fcdcea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QURQonV4eGRDizJ+zcB3mTjgVW6wWe54XDQAzU55HwT2DHf9gBj+pA4VRkCZecNmtQh38oNdrPA9w73s2DxcAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T06:40:17.140679Z","bundle_sha256":"685bd3dbe604613785b6b0f17c6b71a7b0ab7e01540afcdf667cb1acd1d2ccf3"}}