{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RMZTUE4Y5MLWSFAS7ABKKX2ZQT","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":"b1d25ec840d2255989449a7e404feb815fcf297361ba7b96180f493ea0adee1c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T15:16:35Z","title_canon_sha256":"46c03ee5e5baac6b1856496d391a89137c68949c7d476a687cb4cecbaa9befb1"},"schema_version":"1.0","source":{"id":"2506.21367","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.21367","created_at":"2026-07-05T11:27:44Z"},{"alias_kind":"arxiv_version","alias_value":"2506.21367v1","created_at":"2026-07-05T11:27:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21367","created_at":"2026-07-05T11:27:44Z"},{"alias_kind":"pith_short_12","alias_value":"RMZTUE4Y5MLW","created_at":"2026-07-05T11:27:44Z"},{"alias_kind":"pith_short_16","alias_value":"RMZTUE4Y5MLWSFAS","created_at":"2026-07-05T11:27:44Z"},{"alias_kind":"pith_short_8","alias_value":"RMZTUE4Y","created_at":"2026-07-05T11:27:44Z"}],"graph_snapshots":[{"event_id":"sha256:e8f2930e7066825624ba956496ef887b1da79782fc3f7be71231135c07072bb2","target":"graph","created_at":"2026-07-05T11:27:44Z","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/2506.21367/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"rQdia regularizes Q-value distributions with augmented images in pixel-based deep reinforcement learning. With a simple auxiliary loss, that equalizes these distributions via MSE, rQdia boosts DrQ and SAC on 9/12 and 10/12 tasks respectively in the MuJoCo Continuous Control Suite from pixels, and Data-Efficient Rainbow on 18/26 Atari Arcade environments. Gains are measured in both sample efficiency and longer-term training. Moreover, the addition of rQdia finally propels model-free continuous control from pixels over the state encoding baseline.","authors_text":"Jing Bi, Sam Lerman","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T15:16:35Z","title":"rQdia: Regularizing Q-Value Distributions With Image Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21367","kind":"arxiv","version":1},"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":"sha256:481223daa7dbe07dc5a32c320f106c54c342f3bffab9a5ded413920ba15c04a1","target":"record","created_at":"2026-07-05T11:27:44Z","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":"b1d25ec840d2255989449a7e404feb815fcf297361ba7b96180f493ea0adee1c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T15:16:35Z","title_canon_sha256":"46c03ee5e5baac6b1856496d391a89137c68949c7d476a687cb4cecbaa9befb1"},"schema_version":"1.0","source":{"id":"2506.21367","kind":"arxiv","version":1}},"canonical_sha256":"8b333a1398eb17691412f802a55f5984c1abc0a4b6649ddf5fe7e8fcbd193c64","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b333a1398eb17691412f802a55f5984c1abc0a4b6649ddf5fe7e8fcbd193c64","first_computed_at":"2026-07-05T11:27:44.505907Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:27:44.505907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EmuMAh5wuF9RipR23HPtac2N7T7naQQdmCYWpZ0Voe7OTJRAn6CLnC3UHCTSs4k7Zo+ZMvV4nqWSnwk81i0LCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:27:44.506401Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.21367","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:481223daa7dbe07dc5a32c320f106c54c342f3bffab9a5ded413920ba15c04a1","sha256:e8f2930e7066825624ba956496ef887b1da79782fc3f7be71231135c07072bb2"],"state_sha256":"2c99f52aa3dc33a852bd566519e2291e8d5d1fd18590a959852d42795c6bd59c"}