{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:757WQV5ZR5ECYIHNMR5MLG3D7G","short_pith_number":"pith:757WQV5Z","schema_version":"1.0","canonical_sha256":"ff7f6857b98f482c20ed647ac59b63f98768195690d2415aa82a40ec3f8697d4","source":{"kind":"arxiv","id":"1903.10605","version":3},"attestation_state":"computed","paper":{"title":"Q-Learning for Continuous Actions with Cross-Entropy Guided Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ben Eisner, Daniel Lee, Eric Mitchell, Riley Simmons-Edler, Sebastian Seung","submitted_at":"2019-03-25T21:46:58Z","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 "},"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":"1903.10605","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-03-25T21:46:58Z","cross_cats_sorted":[],"title_canon_sha256":"83e4473bc27d274a90d875ea9096b24a601aa05a7d3d5d29f69cc955db56a6c5","abstract_canon_sha256":"ca2c9dc9f78d9276d6f292828220013491a167fd36181478a3cc3a67abe27232"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:42.620789Z","signature_b64":"lBFBIZfr3O6ugeCfETwSeKWol5djWK03hpJZ1Dh/Ny81vPFpjbfjcnid0IBuaJKjS1UP66Vkejt51SuRaGv9DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff7f6857b98f482c20ed647ac59b63f98768195690d2415aa82a40ec3f8697d4","last_reissued_at":"2026-05-17T23:41:42.620310Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:42.620310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Q-Learning for Continuous Actions with Cross-Entropy Guided Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ben Eisner, Daniel Lee, Eric Mitchell, Riley Simmons-Edler, Sebastian Seung","submitted_at":"2019-03-25T21:46:58Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.10605","kind":"arxiv","version":3},"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":"1903.10605","created_at":"2026-05-17T23:41:42.620388+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.10605v3","created_at":"2026-05-17T23:41:42.620388+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.10605","created_at":"2026-05-17T23:41:42.620388+00:00"},{"alias_kind":"pith_short_12","alias_value":"757WQV5ZR5EC","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"757WQV5ZR5ECYIHN","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"757WQV5Z","created_at":"2026-05-18T12:33:12.712433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.03194","citing_title":"Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/757WQV5ZR5ECYIHNMR5MLG3D7G","json":"https://pith.science/pith/757WQV5ZR5ECYIHNMR5MLG3D7G.json","graph_json":"https://pith.science/api/pith-number/757WQV5ZR5ECYIHNMR5MLG3D7G/graph.json","events_json":"https://pith.science/api/pith-number/757WQV5ZR5ECYIHNMR5MLG3D7G/events.json","paper":"https://pith.science/paper/757WQV5Z"},"agent_actions":{"view_html":"https://pith.science/pith/757WQV5ZR5ECYIHNMR5MLG3D7G","download_json":"https://pith.science/pith/757WQV5ZR5ECYIHNMR5MLG3D7G.json","view_paper":"https://pith.science/paper/757WQV5Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.10605&json=true","fetch_graph":"https://pith.science/api/pith-number/757WQV5ZR5ECYIHNMR5MLG3D7G/graph.json","fetch_events":"https://pith.science/api/pith-number/757WQV5ZR5ECYIHNMR5MLG3D7G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/757WQV5ZR5ECYIHNMR5MLG3D7G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/757WQV5ZR5ECYIHNMR5MLG3D7G/action/storage_attestation","attest_author":"https://pith.science/pith/757WQV5ZR5ECYIHNMR5MLG3D7G/action/author_attestation","sign_citation":"https://pith.science/pith/757WQV5ZR5ECYIHNMR5MLG3D7G/action/citation_signature","submit_replication":"https://pith.science/pith/757WQV5ZR5ECYIHNMR5MLG3D7G/action/replication_record"}},"created_at":"2026-05-17T23:41:42.620388+00:00","updated_at":"2026-05-17T23:41:42.620388+00:00"}