{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:P2ICTKPUJCQKS4D3RLZQQPMSZ3","short_pith_number":"pith:P2ICTKPU","canonical_record":{"source":{"id":"1609.05140","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-16T17:05:55Z","cross_cats_sorted":[],"title_canon_sha256":"05d607df2281bf04441a62d104058d2ced7c956a81c687295e12b49b1cb6741c","abstract_canon_sha256":"d5e33147314a89d06d1f73d6a32c7324a8bda2a2fc30a962b8119c89902b3411"},"schema_version":"1.0"},"canonical_sha256":"7e9029a9f448a0a9707b8af3083d92cee7be00fc01e89787195e0d7b555e532a","source":{"kind":"arxiv","id":"1609.05140","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.05140","created_at":"2026-05-18T00:55:57Z"},{"alias_kind":"arxiv_version","alias_value":"1609.05140v2","created_at":"2026-05-18T00:55:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.05140","created_at":"2026-05-18T00:55:57Z"},{"alias_kind":"pith_short_12","alias_value":"P2ICTKPUJCQK","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"P2ICTKPUJCQKS4D3","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"P2ICTKPU","created_at":"2026-05-18T12:30:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:P2ICTKPUJCQKS4D3RLZQQPMSZ3","target":"record","payload":{"canonical_record":{"source":{"id":"1609.05140","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-16T17:05:55Z","cross_cats_sorted":[],"title_canon_sha256":"05d607df2281bf04441a62d104058d2ced7c956a81c687295e12b49b1cb6741c","abstract_canon_sha256":"d5e33147314a89d06d1f73d6a32c7324a8bda2a2fc30a962b8119c89902b3411"},"schema_version":"1.0"},"canonical_sha256":"7e9029a9f448a0a9707b8af3083d92cee7be00fc01e89787195e0d7b555e532a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:55:57.617432Z","signature_b64":"fiqHvn/T/ASHLPAZrIgfp/SCRvhU9ZpfxBfx/Ls3y6F8fQmIPK4Z07116hJhOHLJcSxb8v9BxBX8dSF4yzkFDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e9029a9f448a0a9707b8af3083d92cee7be00fc01e89787195e0d7b555e532a","last_reissued_at":"2026-05-18T00:55:57.616974Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:55:57.616974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1609.05140","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":"2026-05-18T00:55:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R/PWqOLE5mOpYsTdne4z/7Y+JbS00FbwZoXQKghhoicA2RncVt+r9/8MXNFArFiVL61fK09NFLFUIxv0IQ4EBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:14:02.088819Z"},"content_sha256":"83836d9cb9c7ac5c81a92ba9773e2abb7d59baed95dc27c33975d87a4c4c93f1","schema_version":"1.0","event_id":"sha256:83836d9cb9c7ac5c81a92ba9773e2abb7d59baed95dc27c33975d87a4c4c93f1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:P2ICTKPUJCQKS4D3RLZQQPMSZ3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Option-Critic Architecture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Doina Precup, Jean Harb, Pierre-Luc Bacon","submitted_at":"2016-09-16T17:05:55Z","abstract_excerpt":"Temporal abstraction is key to scaling up learning and planning in reinforcement learning. While planning with temporally extended actions is well understood, creating such abstractions autonomously from data has remained challenging. We tackle this problem in the framework of options [Sutton, Precup & Singh, 1999; Precup, 2000]. We derive policy gradient theorems for options and propose a new option-critic architecture capable of learning both the internal policies and the termination conditions of options, in tandem with the policy over options, and without the need to provide any additional"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.05140","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":"2026-05-18T00:55:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XxpHM8p18vLTxG1rR4bIqRB6LzF0S5oRzjPEdDRhfreF0itB/cECwUT2XKiirugDABizEzkK+clk/4BBPIQGCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:14:02.089478Z"},"content_sha256":"ec5f1862587babbbc4c1668b39269604a139a08442dae5fc88102c31d66f153d","schema_version":"1.0","event_id":"sha256:ec5f1862587babbbc4c1668b39269604a139a08442dae5fc88102c31d66f153d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P2ICTKPUJCQKS4D3RLZQQPMSZ3/bundle.json","state_url":"https://pith.science/pith/P2ICTKPUJCQKS4D3RLZQQPMSZ3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P2ICTKPUJCQKS4D3RLZQQPMSZ3/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":"2026-05-25T19:14:02Z","links":{"resolver":"https://pith.science/pith/P2ICTKPUJCQKS4D3RLZQQPMSZ3","bundle":"https://pith.science/pith/P2ICTKPUJCQKS4D3RLZQQPMSZ3/bundle.json","state":"https://pith.science/pith/P2ICTKPUJCQKS4D3RLZQQPMSZ3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P2ICTKPUJCQKS4D3RLZQQPMSZ3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:P2ICTKPUJCQKS4D3RLZQQPMSZ3","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":"d5e33147314a89d06d1f73d6a32c7324a8bda2a2fc30a962b8119c89902b3411","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-16T17:05:55Z","title_canon_sha256":"05d607df2281bf04441a62d104058d2ced7c956a81c687295e12b49b1cb6741c"},"schema_version":"1.0","source":{"id":"1609.05140","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.05140","created_at":"2026-05-18T00:55:57Z"},{"alias_kind":"arxiv_version","alias_value":"1609.05140v2","created_at":"2026-05-18T00:55:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.05140","created_at":"2026-05-18T00:55:57Z"},{"alias_kind":"pith_short_12","alias_value":"P2ICTKPUJCQK","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"P2ICTKPUJCQKS4D3","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"P2ICTKPU","created_at":"2026-05-18T12:30:36Z"}],"graph_snapshots":[{"event_id":"sha256:ec5f1862587babbbc4c1668b39269604a139a08442dae5fc88102c31d66f153d","target":"graph","created_at":"2026-05-18T00:55:57Z","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":"Temporal abstraction is key to scaling up learning and planning in reinforcement learning. While planning with temporally extended actions is well understood, creating such abstractions autonomously from data has remained challenging. We tackle this problem in the framework of options [Sutton, Precup & Singh, 1999; Precup, 2000]. We derive policy gradient theorems for options and propose a new option-critic architecture capable of learning both the internal policies and the termination conditions of options, in tandem with the policy over options, and without the need to provide any additional","authors_text":"Doina Precup, Jean Harb, Pierre-Luc Bacon","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-16T17:05:55Z","title":"The Option-Critic Architecture"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.05140","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":"sha256:83836d9cb9c7ac5c81a92ba9773e2abb7d59baed95dc27c33975d87a4c4c93f1","target":"record","created_at":"2026-05-18T00:55:57Z","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":"d5e33147314a89d06d1f73d6a32c7324a8bda2a2fc30a962b8119c89902b3411","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-16T17:05:55Z","title_canon_sha256":"05d607df2281bf04441a62d104058d2ced7c956a81c687295e12b49b1cb6741c"},"schema_version":"1.0","source":{"id":"1609.05140","kind":"arxiv","version":2}},"canonical_sha256":"7e9029a9f448a0a9707b8af3083d92cee7be00fc01e89787195e0d7b555e532a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e9029a9f448a0a9707b8af3083d92cee7be00fc01e89787195e0d7b555e532a","first_computed_at":"2026-05-18T00:55:57.616974Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:55:57.616974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fiqHvn/T/ASHLPAZrIgfp/SCRvhU9ZpfxBfx/Ls3y6F8fQmIPK4Z07116hJhOHLJcSxb8v9BxBX8dSF4yzkFDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:55:57.617432Z","signed_message":"canonical_sha256_bytes"},"source_id":"1609.05140","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:83836d9cb9c7ac5c81a92ba9773e2abb7d59baed95dc27c33975d87a4c4c93f1","sha256:ec5f1862587babbbc4c1668b39269604a139a08442dae5fc88102c31d66f153d"],"state_sha256":"c40260412364f8c8d5bda1fff8884fbd2215c863ab91f051539a60849213cacd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1vLSQrFsYbs6bO1cwUdFzNgdg2+qC4ZzxzoRWDZ2sFHO2FKIJRzPO29pxQ46/9XgLXuud3WgaVaxPomZFEmRBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T19:14:02.092780Z","bundle_sha256":"ec93cbb28095f3e9b1078a85707c75c642ff5548ed236bf3860e84065c502859"}}