{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:MOYWHB2HFBW5XDHO7EL3KZGI4X","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":"71343c2e20f32e4f22400cbc4344c23b5f65536ba3dc90c68c0b1a22bcce3cf9","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-26T21:16:17Z","title_canon_sha256":"7f7709d67010d7a5668bf43dcc4aa0fa0efa7635bbc571e26b1df3bd57a10fef"},"schema_version":"1.0","source":{"id":"1909.12397","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.12397","created_at":"2026-07-05T00:44:40Z"},{"alias_kind":"arxiv_version","alias_value":"1909.12397v3","created_at":"2026-07-05T00:44:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.12397","created_at":"2026-07-05T00:44:40Z"},{"alias_kind":"pith_short_12","alias_value":"MOYWHB2HFBW5","created_at":"2026-07-05T00:44:40Z"},{"alias_kind":"pith_short_16","alias_value":"MOYWHB2HFBW5XDHO","created_at":"2026-07-05T00:44:40Z"},{"alias_kind":"pith_short_8","alias_value":"MOYWHB2H","created_at":"2026-07-05T00:44:40Z"}],"graph_snapshots":[{"event_id":"sha256:091f50917b38df7971d63ac86dc073b33411c479e1e8f9cc347f7b648cfb2031","target":"graph","created_at":"2026-07-05T00:44:40Z","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/1909.12397/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Value-based reinforcement learning (RL) methods like Q-learning have shown success in a variety of domains. One challenge in applying Q-learning to continuous-action RL problems, however, is the continuous action maximization (max-Q) required for optimal Bellman backup. In this work, we develop CAQL, a (class of) algorithm(s) for continuous-action Q-learning that can use several plug-and-play optimizers for the max-Q problem. Leveraging recent optimization results for deep neural networks, we show that max-Q can be solved optimally using mixed-integer programming (MIP). When the Q-function rep","authors_text":"Christian Tjandraatmadja, Craig Boutilier, Moonkyung Ryu, Ross Anderson, Yinlam Chow","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-26T21:16:17Z","title":"CAQL: Continuous Action Q-Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.12397","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:ee0719e64dba6dd1996451a9d672bc150853f17667a3908460d2c24b6f579e97","target":"record","created_at":"2026-07-05T00:44:40Z","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":"71343c2e20f32e4f22400cbc4344c23b5f65536ba3dc90c68c0b1a22bcce3cf9","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-26T21:16:17Z","title_canon_sha256":"7f7709d67010d7a5668bf43dcc4aa0fa0efa7635bbc571e26b1df3bd57a10fef"},"schema_version":"1.0","source":{"id":"1909.12397","kind":"arxiv","version":3}},"canonical_sha256":"63b1638747286ddb8ceef917b564c8e5e2ef6a8d81df9278f2189d6550cb3e20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63b1638747286ddb8ceef917b564c8e5e2ef6a8d81df9278f2189d6550cb3e20","first_computed_at":"2026-07-05T00:44:40.399410Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:44:40.399410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yUoH+9fqCYje3ezDcKBDkkGFDy/CZ93ctwVHb+Vge4fu2hqUnHKNYvIAMdP7SyxKhukQixuzKH5QiV/aaAEaCg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:44:40.399791Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.12397","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee0719e64dba6dd1996451a9d672bc150853f17667a3908460d2c24b6f579e97","sha256:091f50917b38df7971d63ac86dc073b33411c479e1e8f9cc347f7b648cfb2031"],"state_sha256":"724ecc65f07a8bc58b71578585cf08dfe81bf64b2e9a834b5c2bca85f45dafb2"}