{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:4NWABOF5UHTJQOMVQNN6RVVWB3","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":"893a883be8f7977e05faffce176fd26bb6af2d744dcd6397e74544ecebee37ee","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-21T09:42:41Z","title_canon_sha256":"2cb9ccea37a2aeda9425c2ce2279ab7d1999ef891a4550d7b54b8d250ce8b675"},"schema_version":"1.0","source":{"id":"1903.08894","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.08894","created_at":"2026-05-17T23:50:43Z"},{"alias_kind":"arxiv_version","alias_value":"1903.08894v1","created_at":"2026-05-17T23:50:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.08894","created_at":"2026-05-17T23:50:43Z"},{"alias_kind":"pith_short_12","alias_value":"4NWABOF5UHTJ","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"4NWABOF5UHTJQOMV","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"4NWABOF5","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:7e188c5bdd90e1bcc2663704d5ead0f17b47a4a0ddf90deff852c585ccfe1ea1","target":"graph","created_at":"2026-05-17T23:50:43Z","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":"Deep Q-Learning (DQL), a family of temporal difference algorithms for control, employs three techniques collectively known as the `deadly triad' in reinforcement learning: bootstrapping, off-policy learning, and function approximation. Prior work has demonstrated that together these can lead to divergence in Q-learning algorithms, but the conditions under which divergence occurs are not well-understood. In this note, we give a simple analysis based on a linear approximation to the Q-value updates, which we believe provides insight into divergence under the deadly triad. The central point in ou","authors_text":"Ethan Knight, Joshua Achiam, Pieter Abbeel","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-21T09:42:41Z","title":"Towards Characterizing Divergence in Deep Q-Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.08894","kind":"arxiv","version":1},"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":"sha256:318baa3b7925427d0241c7c9dff3f244e4944fdba12ba7a984e7bc880132df29","target":"record","created_at":"2026-05-17T23:50:43Z","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":"893a883be8f7977e05faffce176fd26bb6af2d744dcd6397e74544ecebee37ee","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-21T09:42:41Z","title_canon_sha256":"2cb9ccea37a2aeda9425c2ce2279ab7d1999ef891a4550d7b54b8d250ce8b675"},"schema_version":"1.0","source":{"id":"1903.08894","kind":"arxiv","version":1}},"canonical_sha256":"e36c00b8bda1e6983995835be8d6b60ed9937553f8ea205d628c42621c67d0cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e36c00b8bda1e6983995835be8d6b60ed9937553f8ea205d628c42621c67d0cf","first_computed_at":"2026-05-17T23:50:43.646611Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:50:43.646611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ETGLZRyip5iyyP9XU2ZF0vHJ3dA15AbvdlEEqzTPpdX1MHpHuRzQpnHf+gAFNdZnJVa6SbY0+2go7imgW75IDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:50:43.647121Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.08894","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:318baa3b7925427d0241c7c9dff3f244e4944fdba12ba7a984e7bc880132df29","sha256:7e188c5bdd90e1bcc2663704d5ead0f17b47a4a0ddf90deff852c585ccfe1ea1"],"state_sha256":"2c0478a29df0c44df1536ea91ed58fb406310400f759c32e59a06456564aaf42"}