{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:HEM62SNUXKDNVNTKGVNKXLVNTG","short_pith_number":"pith:HEM62SNU","schema_version":"1.0","canonical_sha256":"3919ed49b4ba86dab66a355aabaead999f3c7ebb8d5ff22f8312a886f31da5e7","source":{"kind":"arxiv","id":"1907.03876","version":1},"attestation_state":"computed","paper":{"title":"Deep Active Inference as Variational Policy Gradients","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Beren Millidge","submitted_at":"2019-07-08T21:14:29Z","abstract_excerpt":"Active Inference is a theory of action arising from neuroscience which casts action and planning as a bayesian inference problem to be solved by minimizing a single quantity - the variational free energy. Active Inference promises a unifying account of action and perception coupled with a biologically plausible process theory. Despite these potential advantages, current implementations of Active Inference can only handle small, discrete policy and state-spaces and typically require the environmental dynamics to be known. In this paper we propose a novel deep Active Inference algorithm which ap"},"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":"1907.03876","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-08T21:14:29Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"02a37349633b1cf2e373e6cb00fb3d69e7aca3e4d681abee782bf84abab5cf3f","abstract_canon_sha256":"92c3286fd5529a6475b67fc525ea55f9fea1fb5676d0495c653683ecc05482e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:06.505415Z","signature_b64":"NMF90qjN/krCC9YtGbY6jTwmcOxAxJHixSEy6P/VHLA9G/JpM35T4NI/N1YYIV+9fvyIIKZ/+J+YqGSHkmsFBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3919ed49b4ba86dab66a355aabaead999f3c7ebb8d5ff22f8312a886f31da5e7","last_reissued_at":"2026-05-17T23:41:06.504601Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:06.504601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Active Inference as Variational Policy Gradients","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Beren Millidge","submitted_at":"2019-07-08T21:14:29Z","abstract_excerpt":"Active Inference is a theory of action arising from neuroscience which casts action and planning as a bayesian inference problem to be solved by minimizing a single quantity - the variational free energy. Active Inference promises a unifying account of action and perception coupled with a biologically plausible process theory. Despite these potential advantages, current implementations of Active Inference can only handle small, discrete policy and state-spaces and typically require the environmental dynamics to be known. In this paper we propose a novel deep Active Inference algorithm which ap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.03876","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":"1907.03876","created_at":"2026-05-17T23:41:06.504735+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.03876v1","created_at":"2026-05-17T23:41:06.504735+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.03876","created_at":"2026-05-17T23:41:06.504735+00:00"},{"alias_kind":"pith_short_12","alias_value":"HEM62SNUXKDN","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"HEM62SNUXKDNVNTK","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"HEM62SNU","created_at":"2026-05-18T12:33:18.533446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.12536","citing_title":"Information as Maximum-Caliber Deviation: A bridge between Integrated Information Theory and the Free Energy Principle","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HEM62SNUXKDNVNTKGVNKXLVNTG","json":"https://pith.science/pith/HEM62SNUXKDNVNTKGVNKXLVNTG.json","graph_json":"https://pith.science/api/pith-number/HEM62SNUXKDNVNTKGVNKXLVNTG/graph.json","events_json":"https://pith.science/api/pith-number/HEM62SNUXKDNVNTKGVNKXLVNTG/events.json","paper":"https://pith.science/paper/HEM62SNU"},"agent_actions":{"view_html":"https://pith.science/pith/HEM62SNUXKDNVNTKGVNKXLVNTG","download_json":"https://pith.science/pith/HEM62SNUXKDNVNTKGVNKXLVNTG.json","view_paper":"https://pith.science/paper/HEM62SNU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.03876&json=true","fetch_graph":"https://pith.science/api/pith-number/HEM62SNUXKDNVNTKGVNKXLVNTG/graph.json","fetch_events":"https://pith.science/api/pith-number/HEM62SNUXKDNVNTKGVNKXLVNTG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HEM62SNUXKDNVNTKGVNKXLVNTG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HEM62SNUXKDNVNTKGVNKXLVNTG/action/storage_attestation","attest_author":"https://pith.science/pith/HEM62SNUXKDNVNTKGVNKXLVNTG/action/author_attestation","sign_citation":"https://pith.science/pith/HEM62SNUXKDNVNTKGVNKXLVNTG/action/citation_signature","submit_replication":"https://pith.science/pith/HEM62SNUXKDNVNTKGVNKXLVNTG/action/replication_record"}},"created_at":"2026-05-17T23:41:06.504735+00:00","updated_at":"2026-05-17T23:41:06.504735+00:00"}