{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:J4RJKY2BULQ73VJH6CGQ2D4ZNY","short_pith_number":"pith:J4RJKY2B","canonical_record":{"source":{"id":"1902.05605","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-14T21:05:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bacc03e8e0d42cc7ce8fb03536e8d4f632908f0ea8ac1e8f94a7d7ee5c4036b7","abstract_canon_sha256":"b321b73f03dd00040196cb5cd3de7b568993f6bc9a22bbd10224d6c4c2a11605"},"schema_version":"1.0"},"canonical_sha256":"4f22956341a2e1fdd527f08d0d0f996e177552d606fbd129564d27189e3d368e","source":{"kind":"arxiv","id":"1902.05605","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.05605","created_at":"2026-07-05T07:59:44Z"},{"alias_kind":"arxiv_version","alias_value":"1902.05605v4","created_at":"2026-07-05T07:59:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.05605","created_at":"2026-07-05T07:59:44Z"},{"alias_kind":"pith_short_12","alias_value":"J4RJKY2BULQ7","created_at":"2026-07-05T07:59:44Z"},{"alias_kind":"pith_short_16","alias_value":"J4RJKY2BULQ73VJH","created_at":"2026-07-05T07:59:44Z"},{"alias_kind":"pith_short_8","alias_value":"J4RJKY2B","created_at":"2026-07-05T07:59:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:J4RJKY2BULQ73VJH6CGQ2D4ZNY","target":"record","payload":{"canonical_record":{"source":{"id":"1902.05605","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-14T21:05:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bacc03e8e0d42cc7ce8fb03536e8d4f632908f0ea8ac1e8f94a7d7ee5c4036b7","abstract_canon_sha256":"b321b73f03dd00040196cb5cd3de7b568993f6bc9a22bbd10224d6c4c2a11605"},"schema_version":"1.0"},"canonical_sha256":"4f22956341a2e1fdd527f08d0d0f996e177552d606fbd129564d27189e3d368e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:44.778731Z","signature_b64":"x4VE6OZVo3Jd0MZB9FmeK6AyZchCojtYa8hN6PmTgVbTM61oheanCYoEwpaJch1jRG3kzUAFXf8sl3o14km9AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f22956341a2e1fdd527f08d0d0f996e177552d606fbd129564d27189e3d368e","last_reissued_at":"2026-07-05T07:59:44.778146Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:44.778146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.05605","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:59:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WZuA5HtvPi9lq4v8Mm94s5TECV7+v/ha+/xmevCkcb9FhXtRR2osvOwR0gzYhJlb4fpgHqmyn89CuDp4e/4KDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T02:26:58.201663Z"},"content_sha256":"fe64deb9dc22bdc76469e769005bb95d83ce91ab490cdd7ace643a085c600053","schema_version":"1.0","event_id":"sha256:fe64deb9dc22bdc76469e769005bb95d83ce91ab490cdd7ace643a085c600053"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:J4RJKY2BULQ73VJH6CGQ2D4ZNY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aditya Bhatt, Artemij Amiranashvili, Boris Belousov, Daniel Palenicek, Jan Peters, Max Argus, Thomas Brox","submitted_at":"2019-02-14T21:05:50Z","abstract_excerpt":"Sample efficiency is a crucial problem in deep reinforcement learning. Recent algorithms, such as REDQ and DroQ, found a way to improve the sample efficiency by increasing the update-to-data (UTD) ratio to 20 gradient update steps on the critic per environment sample. However, this comes at the expense of a greatly increased computational cost. To reduce this computational burden, we introduce CrossQ: A lightweight algorithm for continuous control tasks that makes careful use of Batch Normalization and removes target networks to surpass the current state-of-the-art in sample efficiency while m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.05605","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1902.05605/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T07:59:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"23wVynazvoDw/ej2n/oNHG7MDvCNM+JMvN4a+uGnS28Jakl3g5blcIdgejN6WA/o5ax4SBPGLrzaeouSI/+uBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T02:26:58.202255Z"},"content_sha256":"3346d357bf2e5dcdad78954050a8f8ff05059b010bfefcd299b0fbf1926308a9","schema_version":"1.0","event_id":"sha256:3346d357bf2e5dcdad78954050a8f8ff05059b010bfefcd299b0fbf1926308a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J4RJKY2BULQ73VJH6CGQ2D4ZNY/bundle.json","state_url":"https://pith.science/pith/J4RJKY2BULQ73VJH6CGQ2D4ZNY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J4RJKY2BULQ73VJH6CGQ2D4ZNY/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":"2026-08-21T02:26:58Z","links":{"resolver":"https://pith.science/pith/J4RJKY2BULQ73VJH6CGQ2D4ZNY","bundle":"https://pith.science/pith/J4RJKY2BULQ73VJH6CGQ2D4ZNY/bundle.json","state":"https://pith.science/pith/J4RJKY2BULQ73VJH6CGQ2D4ZNY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J4RJKY2BULQ73VJH6CGQ2D4ZNY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:J4RJKY2BULQ73VJH6CGQ2D4ZNY","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":"b321b73f03dd00040196cb5cd3de7b568993f6bc9a22bbd10224d6c4c2a11605","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-14T21:05:50Z","title_canon_sha256":"bacc03e8e0d42cc7ce8fb03536e8d4f632908f0ea8ac1e8f94a7d7ee5c4036b7"},"schema_version":"1.0","source":{"id":"1902.05605","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.05605","created_at":"2026-07-05T07:59:44Z"},{"alias_kind":"arxiv_version","alias_value":"1902.05605v4","created_at":"2026-07-05T07:59:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.05605","created_at":"2026-07-05T07:59:44Z"},{"alias_kind":"pith_short_12","alias_value":"J4RJKY2BULQ7","created_at":"2026-07-05T07:59:44Z"},{"alias_kind":"pith_short_16","alias_value":"J4RJKY2BULQ73VJH","created_at":"2026-07-05T07:59:44Z"},{"alias_kind":"pith_short_8","alias_value":"J4RJKY2B","created_at":"2026-07-05T07:59:44Z"}],"graph_snapshots":[{"event_id":"sha256:3346d357bf2e5dcdad78954050a8f8ff05059b010bfefcd299b0fbf1926308a9","target":"graph","created_at":"2026-07-05T07:59:44Z","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/1902.05605/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sample efficiency is a crucial problem in deep reinforcement learning. Recent algorithms, such as REDQ and DroQ, found a way to improve the sample efficiency by increasing the update-to-data (UTD) ratio to 20 gradient update steps on the critic per environment sample. However, this comes at the expense of a greatly increased computational cost. To reduce this computational burden, we introduce CrossQ: A lightweight algorithm for continuous control tasks that makes careful use of Batch Normalization and removes target networks to surpass the current state-of-the-art in sample efficiency while m","authors_text":"Aditya Bhatt, Artemij Amiranashvili, Boris Belousov, Daniel Palenicek, Jan Peters, Max Argus, Thomas Brox","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-14T21:05:50Z","title":"CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.05605","kind":"arxiv","version":4},"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:fe64deb9dc22bdc76469e769005bb95d83ce91ab490cdd7ace643a085c600053","target":"record","created_at":"2026-07-05T07:59:44Z","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":"b321b73f03dd00040196cb5cd3de7b568993f6bc9a22bbd10224d6c4c2a11605","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-14T21:05:50Z","title_canon_sha256":"bacc03e8e0d42cc7ce8fb03536e8d4f632908f0ea8ac1e8f94a7d7ee5c4036b7"},"schema_version":"1.0","source":{"id":"1902.05605","kind":"arxiv","version":4}},"canonical_sha256":"4f22956341a2e1fdd527f08d0d0f996e177552d606fbd129564d27189e3d368e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f22956341a2e1fdd527f08d0d0f996e177552d606fbd129564d27189e3d368e","first_computed_at":"2026-07-05T07:59:44.778146Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:59:44.778146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x4VE6OZVo3Jd0MZB9FmeK6AyZchCojtYa8hN6PmTgVbTM61oheanCYoEwpaJch1jRG3kzUAFXf8sl3o14km9AA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:59:44.778731Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.05605","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe64deb9dc22bdc76469e769005bb95d83ce91ab490cdd7ace643a085c600053","sha256:3346d357bf2e5dcdad78954050a8f8ff05059b010bfefcd299b0fbf1926308a9"],"state_sha256":"79e9ab922f9a57be79fa53fefb78487025070d316d53fbbac704dc3ca5869ae4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HPR6Wn57m3QOM/DEXF3x07AFy+J2DLSWDk2EeAjK1ySKqh2kpKqOQ9g+F05nLn4WAJMRKWsZYVFlnT+ocxGqDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T02:26:58.206243Z","bundle_sha256":"a2269c52f8e8d3ba55c12d9f300214eeb18327dc9e8dc3a2a5bb63ecd5f0c136"}}