{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:757WQV5ZR5ECYIHNMR5MLG3D7G","short_pith_number":"pith:757WQV5Z","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"},"canonical_sha256":"ff7f6857b98f482c20ed647ac59b63f98768195690d2415aa82a40ec3f8697d4","source":{"kind":"arxiv","id":"1903.10605","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:757WQV5ZR5ECYIHNMR5MLG3D7G","target":"record","payload":{"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"},"canonical_sha256":"ff7f6857b98f482c20ed647ac59b63f98768195690d2415aa82a40ec3f8697d4","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"},"source_kind":"arxiv","source_id":"1903.10605","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:41:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TZztIHj2fYEYVGzoYErONKlg6x3xr8WyAkUgLYMdZ4FkGkx5gMMpYjowl1QkfUv07HW1lqYF+H9iGB4ZoALzBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:05:46.512316Z"},"content_sha256":"01f0591b8875f2d8b4384b7e81d06ad8d6494196adb30055dbbd777fa0c98ebb","schema_version":"1.0","event_id":"sha256:01f0591b8875f2d8b4384b7e81d06ad8d6494196adb30055dbbd777fa0c98ebb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:757WQV5ZR5ECYIHNMR5MLG3D7G","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:41:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4G3RnGJkLAq6ZboPLP7HhL1kzqAGT7ONg0/EziWaSKU+r1/spi0D90KUIB+j7FrdQnKLs6XMwDYgqO1GQmGXCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:05:46.512832Z"},"content_sha256":"cad095d944fa30e303c73cd0795b2fad0052f7dc8de80c10c4558d9fb681aa0b","schema_version":"1.0","event_id":"sha256:cad095d944fa30e303c73cd0795b2fad0052f7dc8de80c10c4558d9fb681aa0b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/757WQV5ZR5ECYIHNMR5MLG3D7G/bundle.json","state_url":"https://pith.science/pith/757WQV5ZR5ECYIHNMR5MLG3D7G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/757WQV5ZR5ECYIHNMR5MLG3D7G/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T22:05:46Z","links":{"resolver":"https://pith.science/pith/757WQV5ZR5ECYIHNMR5MLG3D7G","bundle":"https://pith.science/pith/757WQV5ZR5ECYIHNMR5MLG3D7G/bundle.json","state":"https://pith.science/pith/757WQV5ZR5ECYIHNMR5MLG3D7G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/757WQV5ZR5ECYIHNMR5MLG3D7G/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"REIfzU82d3G8K7n9e/D30sBVU9c5I771KKZathpV098ZhTuP5ssxIKyBS3VxwVf3EDL8wdvBaWKar//QtA4PDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:05:46.516918Z","bundle_sha256":"7107fdfb103c1eb074ab2954f4350cf5eaff1a467bddd947a24020f8a4f1e497"}}