{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:FAGNKIXBYVRYJG7WVGIHELI2LF","short_pith_number":"pith:FAGNKIXB","schema_version":"1.0","canonical_sha256":"280cd522e1c563849bf6a990722d1a5951cf5ea488f587a964a74a08272aa464","source":{"kind":"arxiv","id":"1712.00004","version":1},"attestation_state":"computed","paper":{"title":"Learnings Options End-to-End for Continuous Action Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Doina Precup, Jean Harb, Martin Klissarov, Pierre-Luc Bacon","submitted_at":"2017-11-30T00:45:09Z","abstract_excerpt":"We present new results on learning temporally extended actions for continuoustasks, using the options framework (Suttonet al.[1999b], Precup [2000]). In orderto achieve this goal we work with the option-critic architecture (Baconet al.[2017])using a deliberation cost and train it with proximal policy optimization (Schulmanet al.[2017]) instead of vanilla policy gradient. Results on Mujoco domains arepromising, but lead to interesting questions aboutwhena given option should beused, an issue directly connected to the use of initiation sets."},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1712.00004","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-30T00:45:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"33eef5d1aefc833b5507b16deae50ac9d26b06f63d606690a33b57780da391e9","abstract_canon_sha256":"b278ea7870b7bdf930f69a7d8db64d3cebdfcffaf10ecb0971b1a387784e06e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:07.658566Z","signature_b64":"zMhgB9iHRuJqiNEiv4auwF9LWcbaNdkuHKL40yzBZH20HQ9uOF1vTbYLmOTqTREPk3MXv13Y3S58apodvD0QAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"280cd522e1c563849bf6a990722d1a5951cf5ea488f587a964a74a08272aa464","last_reissued_at":"2026-05-18T00:29:07.657863Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:07.657863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learnings Options End-to-End for Continuous Action Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Doina Precup, Jean Harb, Martin Klissarov, Pierre-Luc Bacon","submitted_at":"2017-11-30T00:45:09Z","abstract_excerpt":"We present new results on learning temporally extended actions for continuoustasks, using the options framework (Suttonet al.[1999b], Precup [2000]). In orderto achieve this goal we work with the option-critic architecture (Baconet al.[2017])using a deliberation cost and train it with proximal policy optimization (Schulmanet al.[2017]) instead of vanilla policy gradient. Results on Mujoco domains arepromising, but lead to interesting questions aboutwhena given option should beused, an issue directly connected to the use of initiation sets."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.00004","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1712.00004","created_at":"2026-05-18T00:29:07.657968+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.00004v1","created_at":"2026-05-18T00:29:07.657968+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.00004","created_at":"2026-05-18T00:29:07.657968+00:00"},{"alias_kind":"pith_short_12","alias_value":"FAGNKIXBYVRY","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_16","alias_value":"FAGNKIXBYVRYJG7W","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_8","alias_value":"FAGNKIXB","created_at":"2026-05-18T12:31:15.632608+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1906.10099","citing_title":"DynoPlan: Combining Motion Planning and Deep Neural Network based Controllers for Safe HRL","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2509.00338","citing_title":"Scalable Option Learning in High-Throughput Environments","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24558","citing_title":"Hierarchical Behaviour Spaces","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FAGNKIXBYVRYJG7WVGIHELI2LF","json":"https://pith.science/pith/FAGNKIXBYVRYJG7WVGIHELI2LF.json","graph_json":"https://pith.science/api/pith-number/FAGNKIXBYVRYJG7WVGIHELI2LF/graph.json","events_json":"https://pith.science/api/pith-number/FAGNKIXBYVRYJG7WVGIHELI2LF/events.json","paper":"https://pith.science/paper/FAGNKIXB"},"agent_actions":{"view_html":"https://pith.science/pith/FAGNKIXBYVRYJG7WVGIHELI2LF","download_json":"https://pith.science/pith/FAGNKIXBYVRYJG7WVGIHELI2LF.json","view_paper":"https://pith.science/paper/FAGNKIXB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.00004&json=true","fetch_graph":"https://pith.science/api/pith-number/FAGNKIXBYVRYJG7WVGIHELI2LF/graph.json","fetch_events":"https://pith.science/api/pith-number/FAGNKIXBYVRYJG7WVGIHELI2LF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FAGNKIXBYVRYJG7WVGIHELI2LF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FAGNKIXBYVRYJG7WVGIHELI2LF/action/storage_attestation","attest_author":"https://pith.science/pith/FAGNKIXBYVRYJG7WVGIHELI2LF/action/author_attestation","sign_citation":"https://pith.science/pith/FAGNKIXBYVRYJG7WVGIHELI2LF/action/citation_signature","submit_replication":"https://pith.science/pith/FAGNKIXBYVRYJG7WVGIHELI2LF/action/replication_record"}},"created_at":"2026-05-18T00:29:07.657968+00:00","updated_at":"2026-05-18T00:29:07.657968+00:00"}