{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:IV6IQ7MMMTAQ37JBEVBDJ54V5X","short_pith_number":"pith:IV6IQ7MM","canonical_record":{"source":{"id":"1611.06824","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-21T15:05:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"73fc6cd5265459040ea7aa290444c6a0dfb845c1736a47f7a6504b38518acede","abstract_canon_sha256":"63354b007ff9011b6096f3e2567c9be3a7786cc1b2a909587313438cc5c6f5b3"},"schema_version":"1.0"},"canonical_sha256":"457c887d8c64c10dfd21254234f795edc693e856bbe84c8f8dd51fd84c4eaf85","source":{"kind":"arxiv","id":"1611.06824","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.06824","created_at":"2026-05-18T00:50:12Z"},{"alias_kind":"arxiv_version","alias_value":"1611.06824v3","created_at":"2026-05-18T00:50:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.06824","created_at":"2026-05-18T00:50:12Z"},{"alias_kind":"pith_short_12","alias_value":"IV6IQ7MMMTAQ","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_16","alias_value":"IV6IQ7MMMTAQ37JB","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_8","alias_value":"IV6IQ7MM","created_at":"2026-05-18T12:30:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:IV6IQ7MMMTAQ37JBEVBDJ54V5X","target":"record","payload":{"canonical_record":{"source":{"id":"1611.06824","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-21T15:05:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"73fc6cd5265459040ea7aa290444c6a0dfb845c1736a47f7a6504b38518acede","abstract_canon_sha256":"63354b007ff9011b6096f3e2567c9be3a7786cc1b2a909587313438cc5c6f5b3"},"schema_version":"1.0"},"canonical_sha256":"457c887d8c64c10dfd21254234f795edc693e856bbe84c8f8dd51fd84c4eaf85","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:50:12.299044Z","signature_b64":"BO4sTqmg722xh9g5nx7mN2u8rKkaDSRAKdAhbqsrNW1tRFRdjBH16Mibg2NrxrePJ2Z+ekj7HEfEn1Dy8xn5DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"457c887d8c64c10dfd21254234f795edc693e856bbe84c8f8dd51fd84c4eaf85","last_reissued_at":"2026-05-18T00:50:12.298645Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:50:12.298645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.06824","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:50:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mDuSqYi2Li60/EAfqf3+gX/qwAipjf0uuYIfUDwL1dM2cF+m3VSYI7px7PtgJX3BZ0yd2wIbyKmNfuZO3xu5BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T21:38:55.172152Z"},"content_sha256":"9316bfcbb94cef8fac8a9e47ee2bb38e2d24a6d55bee2d69288cc32c1a34cebd","schema_version":"1.0","event_id":"sha256:9316bfcbb94cef8fac8a9e47ee2bb38e2d24a6d55bee2d69288cc32c1a34cebd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:IV6IQ7MMMTAQ37JBEVBDJ54V5X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Options Discovery with Budgeted Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aur\\'elia L\\'eon, Ludovic Denoyer","submitted_at":"2016-11-21T15:05:55Z","abstract_excerpt":"We consider the problem of learning hierarchical policies for Reinforcement Learning able to discover options, an option corresponding to a sub-policy over a set of primitive actions. Different models have been proposed during the last decade that usually rely on a predefined set of options. We specifically address the problem of automatically discovering options in decision processes. We describe a new learning model called Budgeted Option Neural Network (BONN) able to discover options based on a budgeted learning objective. The BONN model is evaluated on different classical RL problems, demo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.06824","kind":"arxiv","version":3},"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":"2026-05-18T00:50:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pzBO0NELQD+aKATMI4mLfsM+FMjs0CezZArVRqA1JGVsq2NfJPiuI0nfyb1N2ZclUmQevWLvV+aJc08+nmRzAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T21:38:55.172532Z"},"content_sha256":"a19033b9bb79146e4de2ce50a6082d983c71ac5f55980b0b39f3fbaa9e0483f9","schema_version":"1.0","event_id":"sha256:a19033b9bb79146e4de2ce50a6082d983c71ac5f55980b0b39f3fbaa9e0483f9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IV6IQ7MMMTAQ37JBEVBDJ54V5X/bundle.json","state_url":"https://pith.science/pith/IV6IQ7MMMTAQ37JBEVBDJ54V5X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IV6IQ7MMMTAQ37JBEVBDJ54V5X/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":"2026-05-27T21:38:55Z","links":{"resolver":"https://pith.science/pith/IV6IQ7MMMTAQ37JBEVBDJ54V5X","bundle":"https://pith.science/pith/IV6IQ7MMMTAQ37JBEVBDJ54V5X/bundle.json","state":"https://pith.science/pith/IV6IQ7MMMTAQ37JBEVBDJ54V5X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IV6IQ7MMMTAQ37JBEVBDJ54V5X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:IV6IQ7MMMTAQ37JBEVBDJ54V5X","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":"63354b007ff9011b6096f3e2567c9be3a7786cc1b2a909587313438cc5c6f5b3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-21T15:05:55Z","title_canon_sha256":"73fc6cd5265459040ea7aa290444c6a0dfb845c1736a47f7a6504b38518acede"},"schema_version":"1.0","source":{"id":"1611.06824","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.06824","created_at":"2026-05-18T00:50:12Z"},{"alias_kind":"arxiv_version","alias_value":"1611.06824v3","created_at":"2026-05-18T00:50:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.06824","created_at":"2026-05-18T00:50:12Z"},{"alias_kind":"pith_short_12","alias_value":"IV6IQ7MMMTAQ","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_16","alias_value":"IV6IQ7MMMTAQ37JB","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_8","alias_value":"IV6IQ7MM","created_at":"2026-05-18T12:30:22Z"}],"graph_snapshots":[{"event_id":"sha256:a19033b9bb79146e4de2ce50a6082d983c71ac5f55980b0b39f3fbaa9e0483f9","target":"graph","created_at":"2026-05-18T00:50:12Z","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 consider the problem of learning hierarchical policies for Reinforcement Learning able to discover options, an option corresponding to a sub-policy over a set of primitive actions. Different models have been proposed during the last decade that usually rely on a predefined set of options. We specifically address the problem of automatically discovering options in decision processes. We describe a new learning model called Budgeted Option Neural Network (BONN) able to discover options based on a budgeted learning objective. The BONN model is evaluated on different classical RL problems, demo","authors_text":"Aur\\'elia L\\'eon, Ludovic Denoyer","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-21T15:05:55Z","title":"Options Discovery with Budgeted Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.06824","kind":"arxiv","version":3},"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":"sha256:9316bfcbb94cef8fac8a9e47ee2bb38e2d24a6d55bee2d69288cc32c1a34cebd","target":"record","created_at":"2026-05-18T00:50:12Z","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":"63354b007ff9011b6096f3e2567c9be3a7786cc1b2a909587313438cc5c6f5b3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-21T15:05:55Z","title_canon_sha256":"73fc6cd5265459040ea7aa290444c6a0dfb845c1736a47f7a6504b38518acede"},"schema_version":"1.0","source":{"id":"1611.06824","kind":"arxiv","version":3}},"canonical_sha256":"457c887d8c64c10dfd21254234f795edc693e856bbe84c8f8dd51fd84c4eaf85","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"457c887d8c64c10dfd21254234f795edc693e856bbe84c8f8dd51fd84c4eaf85","first_computed_at":"2026-05-18T00:50:12.298645Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:50:12.298645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BO4sTqmg722xh9g5nx7mN2u8rKkaDSRAKdAhbqsrNW1tRFRdjBH16Mibg2NrxrePJ2Z+ekj7HEfEn1Dy8xn5DQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:50:12.299044Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.06824","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9316bfcbb94cef8fac8a9e47ee2bb38e2d24a6d55bee2d69288cc32c1a34cebd","sha256:a19033b9bb79146e4de2ce50a6082d983c71ac5f55980b0b39f3fbaa9e0483f9"],"state_sha256":"8fe5d33ccd70c1a70640226c7e8f64bf4751800cab4af515b50f3347c458e77e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eBqZ8LjG6XssFp9pzvCE5QVeNz85iIlDoqz94uiO2F7IVXMIN3+u4ZWnDf51qBxG3wx+h98v3avS0bPqWNaVAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T21:38:55.175028Z","bundle_sha256":"989c46da591fcf42c56bc569dc566ff4192c82f366eea54e08b987ce98262179"}}