{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:EQQPHUFXEEAU4FOR6XZYD3TOOU","short_pith_number":"pith:EQQPHUFX","schema_version":"1.0","canonical_sha256":"2420f3d0b721014e15d1f5f381ee6e751b405021952c09c689750a3dad14098d","source":{"kind":"arxiv","id":"1807.10299","version":1},"attestation_state":"computed","paper":{"title":"Variational Option Discovery Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dario Amodei, Harrison Edwards, Joshua Achiam, Pieter Abbeel","submitted_at":"2018-07-26T18:05:45Z","abstract_excerpt":"We explore methods for option discovery based on variational inference and make two algorithmic contributions. First: we highlight a tight connection between variational option discovery methods and variational autoencoders, and introduce Variational Autoencoding Learning of Options by Reinforcement (VALOR), a new method derived from the connection. In VALOR, the policy encodes contexts from a noise distribution into trajectories, and the decoder recovers the contexts from the complete trajectories. Second: we propose a curriculum learning approach where the number of contexts seen by the agen"},"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":"1807.10299","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-07-26T18:05:45Z","cross_cats_sorted":[],"title_canon_sha256":"f92e74466a9c2c8b01d825d30a4b85e1e9acbb589fcf2fa3a93a135b8e1ed599","abstract_canon_sha256":"9000987d36c2dbcd637264696fa4524a7d03abb91372537d55d55c3900fc5325"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:41.037705Z","signature_b64":"o64b9wlSaEE0+WhCbkJBJdke0jl/h/fACZeSzyQFIddFLasbc8m7kLpT0jAS2Zm9kwp7z/5yFf/hitcSwx49BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2420f3d0b721014e15d1f5f381ee6e751b405021952c09c689750a3dad14098d","last_reissued_at":"2026-05-18T00:09:41.037179Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:41.037179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variational Option Discovery Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dario Amodei, Harrison Edwards, Joshua Achiam, Pieter Abbeel","submitted_at":"2018-07-26T18:05:45Z","abstract_excerpt":"We explore methods for option discovery based on variational inference and make two algorithmic contributions. First: we highlight a tight connection between variational option discovery methods and variational autoencoders, and introduce Variational Autoencoding Learning of Options by Reinforcement (VALOR), a new method derived from the connection. In VALOR, the policy encodes contexts from a noise distribution into trajectories, and the decoder recovers the contexts from the complete trajectories. Second: we propose a curriculum learning approach where the number of contexts seen by the agen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.10299","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":"1807.10299","created_at":"2026-05-18T00:09:41.037256+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.10299v1","created_at":"2026-05-18T00:09:41.037256+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.10299","created_at":"2026-05-18T00:09:41.037256+00:00"},{"alias_kind":"pith_short_12","alias_value":"EQQPHUFXEEAU","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"EQQPHUFXEEAU4FOR","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"EQQPHUFX","created_at":"2026-05-18T12:32:22.470017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1906.09205","citing_title":"Continual Reinforcement Learning with Diversity Exploration and Adversarial Self-Correction","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"1907.06143","citing_title":"Neural Embedding for Physical Manipulations","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2502.03752","citing_title":"Self-Improving Skill Learning for Robust Skill-based Meta-Reinforcement Learning","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11387","citing_title":"Behavioral Mode Discovery for Fine-tuning Multimodal Generative Policies","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08450","citing_title":"Zero-shot Imitation Learning by Latent Topology Mapping","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24127","citing_title":"Leveraging Human Feedback for Semantically-Relevant Skill Discovery","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06145","citing_title":"Unifying Goal-Conditioned RL and Unsupervised Skill Learning via Control-Maximization","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01862","citing_title":"QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EQQPHUFXEEAU4FOR6XZYD3TOOU","json":"https://pith.science/pith/EQQPHUFXEEAU4FOR6XZYD3TOOU.json","graph_json":"https://pith.science/api/pith-number/EQQPHUFXEEAU4FOR6XZYD3TOOU/graph.json","events_json":"https://pith.science/api/pith-number/EQQPHUFXEEAU4FOR6XZYD3TOOU/events.json","paper":"https://pith.science/paper/EQQPHUFX"},"agent_actions":{"view_html":"https://pith.science/pith/EQQPHUFXEEAU4FOR6XZYD3TOOU","download_json":"https://pith.science/pith/EQQPHUFXEEAU4FOR6XZYD3TOOU.json","view_paper":"https://pith.science/paper/EQQPHUFX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.10299&json=true","fetch_graph":"https://pith.science/api/pith-number/EQQPHUFXEEAU4FOR6XZYD3TOOU/graph.json","fetch_events":"https://pith.science/api/pith-number/EQQPHUFXEEAU4FOR6XZYD3TOOU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EQQPHUFXEEAU4FOR6XZYD3TOOU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EQQPHUFXEEAU4FOR6XZYD3TOOU/action/storage_attestation","attest_author":"https://pith.science/pith/EQQPHUFXEEAU4FOR6XZYD3TOOU/action/author_attestation","sign_citation":"https://pith.science/pith/EQQPHUFXEEAU4FOR6XZYD3TOOU/action/citation_signature","submit_replication":"https://pith.science/pith/EQQPHUFXEEAU4FOR6XZYD3TOOU/action/replication_record"}},"created_at":"2026-05-18T00:09:41.037256+00:00","updated_at":"2026-05-18T00:09:41.037256+00:00"}