{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:LPPMRDU7FMRRZ2YLTZ3EZWARNK","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":"eb44181722d6a2cfcefb94bcb01f5f86b30eab13d91f2bb598daa404d3e73009","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-13T16:10:03Z","title_canon_sha256":"df2f462447a6d6350e71aaae8be5ade9328089a80b1993024c194c884cbcee77"},"schema_version":"1.0","source":{"id":"2006.10524","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.10524","created_at":"2026-07-05T01:16:15Z"},{"alias_kind":"arxiv_version","alias_value":"2006.10524v3","created_at":"2026-07-05T01:16:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.10524","created_at":"2026-07-05T01:16:15Z"},{"alias_kind":"pith_short_12","alias_value":"LPPMRDU7FMRR","created_at":"2026-07-05T01:16:15Z"},{"alias_kind":"pith_short_16","alias_value":"LPPMRDU7FMRRZ2YL","created_at":"2026-07-05T01:16:15Z"},{"alias_kind":"pith_short_8","alias_value":"LPPMRDU7","created_at":"2026-07-05T01:16:15Z"}],"graph_snapshots":[{"event_id":"sha256:a6cea9bf50c62713cc322c5bc10f034543b1d732e538cc004d166add70e8462d","target":"graph","created_at":"2026-07-05T01:16:15Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2006.10524/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There are several ways to categorise reinforcement learning (RL) algorithms, such as either model-based or model-free, policy-based or planning-based, on-policy or off-policy, and online or offline. Broad classification schemes such as these help provide a unified perspective on disparate techniques and can contextualise and guide the development of new algorithms. In this paper, we utilise the control as inference framework to outline a novel classification scheme based on amortised and iterative inference. We demonstrate that a wide range of algorithms can be classified in this manner provid","authors_text":"Alexander Tschantz, Anil K Seth, Beren Millidge, Christopher L Buckley","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-13T16:10:03Z","title":"Reinforcement Learning as Iterative and Amortised Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.10524","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":"sha256:95894fec864d0fc0fb2d897296714b13abc3397dd5c68133b0f39626170a67a1","target":"record","created_at":"2026-07-05T01:16:15Z","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":"eb44181722d6a2cfcefb94bcb01f5f86b30eab13d91f2bb598daa404d3e73009","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-13T16:10:03Z","title_canon_sha256":"df2f462447a6d6350e71aaae8be5ade9328089a80b1993024c194c884cbcee77"},"schema_version":"1.0","source":{"id":"2006.10524","kind":"arxiv","version":3}},"canonical_sha256":"5bdec88e9f2b231ceb0b9e764cd8116a8577006b87c6ff6306434b73b231482a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5bdec88e9f2b231ceb0b9e764cd8116a8577006b87c6ff6306434b73b231482a","first_computed_at":"2026-07-05T01:16:15.997863Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:16:15.997863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CZB+9cdUOso///CrpW5On/X7IBazP2wJSJUxsPIQeZpLpccOFk2/0oXKgNE8gCVq2WM0GsDKJ6y+71rPvEoYDw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:16:15.998224Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.10524","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95894fec864d0fc0fb2d897296714b13abc3397dd5c68133b0f39626170a67a1","sha256:a6cea9bf50c62713cc322c5bc10f034543b1d732e538cc004d166add70e8462d"],"state_sha256":"be879ac7bb03bd8a1d363542a2d0aea1748cffc61530cb082f6aea5d09fc2136"}