{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:I4LH3MNBFIK2KTXUXW4MYF4YR6","short_pith_number":"pith:I4LH3MNB","schema_version":"1.0","canonical_sha256":"47167db1a12a15a54ef4bdb8cc17988fb370d7d2a427219fb6e6728253e0ef0f","source":{"kind":"arxiv","id":"2007.05838","version":1},"attestation_state":"computed","paper":{"title":"Control as Hybrid Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Tschantz, Anil K. Seth, Beren Millidge, Christopher L. Buckley","submitted_at":"2020-07-11T19:44:09Z","abstract_excerpt":"The field of reinforcement learning can be split into model-based and model-free methods. Here, we unify these approaches by casting model-free policy optimisation as amortised variational inference, and model-based planning as iterative variational inference, within a `control as hybrid inference' (CHI) framework. We present an implementation of CHI which naturally mediates the balance between iterative and amortised inference. Using a didactic experiment, we demonstrate that the proposed algorithm operates in a model-based manner at the onset of learning, before converging to a model-free al"},"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":"2007.05838","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-11T19:44:09Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"9913dd8a8bca91fc881c1c9d652493409ed348b72d5858051973dbf34c5bee15","abstract_canon_sha256":"afa0841ea4e1e78f317ad48fd8eb80f0cca7c3e1d13b3239514e7acf359c6fc9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:18:07.245787Z","signature_b64":"YN5fJHR9BftbC1czHawd4yMmOyXmcoJWCIS0miumU/ju+IjDkwPzuQfsWCaXAojFXs3CeXZMAQU8IO5f5fCtDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47167db1a12a15a54ef4bdb8cc17988fb370d7d2a427219fb6e6728253e0ef0f","last_reissued_at":"2026-07-05T01:18:07.245369Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:18:07.245369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Control as Hybrid Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Tschantz, Anil K. Seth, Beren Millidge, Christopher L. Buckley","submitted_at":"2020-07-11T19:44:09Z","abstract_excerpt":"The field of reinforcement learning can be split into model-based and model-free methods. Here, we unify these approaches by casting model-free policy optimisation as amortised variational inference, and model-based planning as iterative variational inference, within a `control as hybrid inference' (CHI) framework. We present an implementation of CHI which naturally mediates the balance between iterative and amortised inference. Using a didactic experiment, we demonstrate that the proposed algorithm operates in a model-based manner at the onset of learning, before converging to a model-free al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.05838","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2007.05838/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2007.05838","created_at":"2026-07-05T01:18:07.245434+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.05838v1","created_at":"2026-07-05T01:18:07.245434+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.05838","created_at":"2026-07-05T01:18:07.245434+00:00"},{"alias_kind":"pith_short_12","alias_value":"I4LH3MNBFIK2","created_at":"2026-07-05T01:18:07.245434+00:00"},{"alias_kind":"pith_short_16","alias_value":"I4LH3MNBFIK2KTXU","created_at":"2026-07-05T01:18:07.245434+00:00"},{"alias_kind":"pith_short_8","alias_value":"I4LH3MNB","created_at":"2026-07-05T01:18:07.245434+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I4LH3MNBFIK2KTXUXW4MYF4YR6","json":"https://pith.science/pith/I4LH3MNBFIK2KTXUXW4MYF4YR6.json","graph_json":"https://pith.science/api/pith-number/I4LH3MNBFIK2KTXUXW4MYF4YR6/graph.json","events_json":"https://pith.science/api/pith-number/I4LH3MNBFIK2KTXUXW4MYF4YR6/events.json","paper":"https://pith.science/paper/I4LH3MNB"},"agent_actions":{"view_html":"https://pith.science/pith/I4LH3MNBFIK2KTXUXW4MYF4YR6","download_json":"https://pith.science/pith/I4LH3MNBFIK2KTXUXW4MYF4YR6.json","view_paper":"https://pith.science/paper/I4LH3MNB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.05838&json=true","fetch_graph":"https://pith.science/api/pith-number/I4LH3MNBFIK2KTXUXW4MYF4YR6/graph.json","fetch_events":"https://pith.science/api/pith-number/I4LH3MNBFIK2KTXUXW4MYF4YR6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I4LH3MNBFIK2KTXUXW4MYF4YR6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I4LH3MNBFIK2KTXUXW4MYF4YR6/action/storage_attestation","attest_author":"https://pith.science/pith/I4LH3MNBFIK2KTXUXW4MYF4YR6/action/author_attestation","sign_citation":"https://pith.science/pith/I4LH3MNBFIK2KTXUXW4MYF4YR6/action/citation_signature","submit_replication":"https://pith.science/pith/I4LH3MNBFIK2KTXUXW4MYF4YR6/action/replication_record"}},"created_at":"2026-07-05T01:18:07.245434+00:00","updated_at":"2026-07-05T01:18:07.245434+00:00"}