{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:757WQV5ZR5ECYIHNMR5MLG3D7G","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":"ca2c9dc9f78d9276d6f292828220013491a167fd36181478a3cc3a67abe27232","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-03-25T21:46:58Z","title_canon_sha256":"83e4473bc27d274a90d875ea9096b24a601aa05a7d3d5d29f69cc955db56a6c5"},"schema_version":"1.0","source":{"id":"1903.10605","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.10605","created_at":"2026-05-17T23:41:42Z"},{"alias_kind":"arxiv_version","alias_value":"1903.10605v3","created_at":"2026-05-17T23:41:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.10605","created_at":"2026-05-17T23:41:42Z"},{"alias_kind":"pith_short_12","alias_value":"757WQV5ZR5EC","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"757WQV5ZR5ECYIHN","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"757WQV5Z","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:cad095d944fa30e303c73cd0795b2fad0052f7dc8de80c10c4558d9fb681aa0b","target":"graph","created_at":"2026-05-17T23:41:42Z","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":"Off-Policy reinforcement learning (RL) is an important class of methods for many problem domains, such as robotics, where the cost of collecting data is high and on-policy methods are consequently intractable. Standard methods for applying Q-learning to continuous-valued action domains involve iteratively sampling the Q-function to find a good action (e.g. via hill-climbing), or by learning a policy network at the same time as the Q-function (e.g. DDPG). Both approaches make tradeoffs between stability, speed, and accuracy. We propose a novel approach, called Cross-Entropy Guided Policies, or ","authors_text":"Ben Eisner, Daniel Lee, Eric Mitchell, Riley Simmons-Edler, Sebastian Seung","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-03-25T21:46:58Z","title":"Q-Learning for Continuous Actions with Cross-Entropy Guided Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.10605","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":"sha256:01f0591b8875f2d8b4384b7e81d06ad8d6494196adb30055dbbd777fa0c98ebb","target":"record","created_at":"2026-05-17T23:41:42Z","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":"ca2c9dc9f78d9276d6f292828220013491a167fd36181478a3cc3a67abe27232","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-03-25T21:46:58Z","title_canon_sha256":"83e4473bc27d274a90d875ea9096b24a601aa05a7d3d5d29f69cc955db56a6c5"},"schema_version":"1.0","source":{"id":"1903.10605","kind":"arxiv","version":3}},"canonical_sha256":"ff7f6857b98f482c20ed647ac59b63f98768195690d2415aa82a40ec3f8697d4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff7f6857b98f482c20ed647ac59b63f98768195690d2415aa82a40ec3f8697d4","first_computed_at":"2026-05-17T23:41:42.620310Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:42.620310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lBFBIZfr3O6ugeCfETwSeKWol5djWK03hpJZ1Dh/Ny81vPFpjbfjcnid0IBuaJKjS1UP66Vkejt51SuRaGv9DA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:42.620789Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.10605","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:01f0591b8875f2d8b4384b7e81d06ad8d6494196adb30055dbbd777fa0c98ebb","sha256:cad095d944fa30e303c73cd0795b2fad0052f7dc8de80c10c4558d9fb681aa0b"],"state_sha256":"5374d839ce9bd78d660f656f1aa2a3fec85a3d64572ff11b0c06cad176d4259e"}