{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:FAGNKIXBYVRYJG7WVGIHELI2LF","short_pith_number":"pith:FAGNKIXB","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"},"canonical_sha256":"280cd522e1c563849bf6a990722d1a5951cf5ea488f587a964a74a08272aa464","source":{"kind":"arxiv","id":"1712.00004","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.00004","created_at":"2026-05-18T00:29:07Z"},{"alias_kind":"arxiv_version","alias_value":"1712.00004v1","created_at":"2026-05-18T00:29:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.00004","created_at":"2026-05-18T00:29:07Z"},{"alias_kind":"pith_short_12","alias_value":"FAGNKIXBYVRY","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"FAGNKIXBYVRYJG7W","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"FAGNKIXB","created_at":"2026-05-18T12:31:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:FAGNKIXBYVRYJG7WVGIHELI2LF","target":"record","payload":{"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"},"canonical_sha256":"280cd522e1c563849bf6a990722d1a5951cf5ea488f587a964a74a08272aa464","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"},"source_kind":"arxiv","source_id":"1712.00004","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":"2026-05-18T00:29:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ez9yNrRGZXbCy70/Ht2SYayF6EFdgNa8sGRZ/ysnyRagLouyZRyo8jANbZe9o95YGD+iu0XgODHnwA+YyhQpCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T08:57:08.382693Z"},"content_sha256":"7e4e910686f2f53e48211b7638a25bb8972427908c82121d9a5e89a6fea3c25a","schema_version":"1.0","event_id":"sha256:7e4e910686f2f53e48211b7638a25bb8972427908c82121d9a5e89a6fea3c25a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:FAGNKIXBYVRYJG7WVGIHELI2LF","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:29:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4cBJ/VN+jx+0D9uIKXNCLgFflbkfVEkgqqodCAa6DFB2xVCQGyiiSbVhcvxGTM5VGbooJdumGBEcxPbFo7tODg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T08:57:08.383205Z"},"content_sha256":"fae6af0f7af0272884333e73a6072422f6589a610b3d06b512f28c6f99acb77e","schema_version":"1.0","event_id":"sha256:fae6af0f7af0272884333e73a6072422f6589a610b3d06b512f28c6f99acb77e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FAGNKIXBYVRYJG7WVGIHELI2LF/bundle.json","state_url":"https://pith.science/pith/FAGNKIXBYVRYJG7WVGIHELI2LF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FAGNKIXBYVRYJG7WVGIHELI2LF/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":"2026-05-25T08:57:08Z","links":{"resolver":"https://pith.science/pith/FAGNKIXBYVRYJG7WVGIHELI2LF","bundle":"https://pith.science/pith/FAGNKIXBYVRYJG7WVGIHELI2LF/bundle.json","state":"https://pith.science/pith/FAGNKIXBYVRYJG7WVGIHELI2LF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FAGNKIXBYVRYJG7WVGIHELI2LF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:FAGNKIXBYVRYJG7WVGIHELI2LF","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":"b278ea7870b7bdf930f69a7d8db64d3cebdfcffaf10ecb0971b1a387784e06e7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-30T00:45:09Z","title_canon_sha256":"33eef5d1aefc833b5507b16deae50ac9d26b06f63d606690a33b57780da391e9"},"schema_version":"1.0","source":{"id":"1712.00004","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.00004","created_at":"2026-05-18T00:29:07Z"},{"alias_kind":"arxiv_version","alias_value":"1712.00004v1","created_at":"2026-05-18T00:29:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.00004","created_at":"2026-05-18T00:29:07Z"},{"alias_kind":"pith_short_12","alias_value":"FAGNKIXBYVRY","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"FAGNKIXBYVRYJG7W","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"FAGNKIXB","created_at":"2026-05-18T12:31:15Z"}],"graph_snapshots":[{"event_id":"sha256:fae6af0f7af0272884333e73a6072422f6589a610b3d06b512f28c6f99acb77e","target":"graph","created_at":"2026-05-18T00:29:07Z","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 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.","authors_text":"Doina Precup, Jean Harb, Martin Klissarov, Pierre-Luc Bacon","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-30T00:45:09Z","title":"Learnings Options End-to-End for Continuous Action Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.00004","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":"sha256:7e4e910686f2f53e48211b7638a25bb8972427908c82121d9a5e89a6fea3c25a","target":"record","created_at":"2026-05-18T00:29:07Z","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":"b278ea7870b7bdf930f69a7d8db64d3cebdfcffaf10ecb0971b1a387784e06e7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-30T00:45:09Z","title_canon_sha256":"33eef5d1aefc833b5507b16deae50ac9d26b06f63d606690a33b57780da391e9"},"schema_version":"1.0","source":{"id":"1712.00004","kind":"arxiv","version":1}},"canonical_sha256":"280cd522e1c563849bf6a990722d1a5951cf5ea488f587a964a74a08272aa464","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"280cd522e1c563849bf6a990722d1a5951cf5ea488f587a964a74a08272aa464","first_computed_at":"2026-05-18T00:29:07.657863Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:29:07.657863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zMhgB9iHRuJqiNEiv4auwF9LWcbaNdkuHKL40yzBZH20HQ9uOF1vTbYLmOTqTREPk3MXv13Y3S58apodvD0QAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:29:07.658566Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.00004","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e4e910686f2f53e48211b7638a25bb8972427908c82121d9a5e89a6fea3c25a","sha256:fae6af0f7af0272884333e73a6072422f6589a610b3d06b512f28c6f99acb77e"],"state_sha256":"39d94cedb69550e51f3dbed81427a9a59d989943683c7145108cba08ab23e116"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w1Vg8wHaFnJ4l+/uy4L8QDuottD5zE6iIAJkM5f/fIyn6HFDnMEPife8s0sOmWskdA/VUD6URC5l8LQ2qOhADQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T08:57:08.386475Z","bundle_sha256":"519fd1e09f208a48c7b1d11e34e4123e80917abcdf0fa25daa19f7356e5a2f65"}}