{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VWMW33TEU2XC5FDVEFP2JFAVQI","short_pith_number":"pith:VWMW33TE","schema_version":"1.0","canonical_sha256":"ad996dee64a6ae2e9475215fa49415820ba0224d77716d04465b15fc13b451c7","source":{"kind":"arxiv","id":"2606.21297","version":1},"attestation_state":"computed","paper":{"title":"NASDAQ: Normalized Observation Space Dynamics-Augmented Q-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"(2) EPFL, (3) Purdue University, China, Jianting Zhang (3), Junyuan Liang (1), Switzerland, USA), Wuhui Chen (1) ((1) Sun Yat-sen University, Xinwei Liu (1), Zicong Hong (2)","submitted_at":"2026-06-19T10:21:04Z","abstract_excerpt":"Augmenting model-free reinforcement learning (RL) with representations learned through observation dynamics prediction (observation-predictive RL) can improve sample efficiency and performance, with minor modifications and limited additional computation. However, this approach still struggles in challenging tasks with low-dimensional observations. In this paper, we identify a key factor behind this problem: unbalanced reconstruction losses across observation dimensions, where dimensions with larger value ranges dominate the loss. This encourages the agent to neglect dimensions with relatively "},"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":"2606.21297","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T10:21:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2bc0ee5cab85427095544dd8c60f8e91d7e5d3ee62d5401c59e3e7c29c44c58e","abstract_canon_sha256":"724831bd889a03ef4e94fd8d9da024d6aa484ab6017247f1f8a8c05bb690933b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:12:36.365607Z","signature_b64":"wSsJMUAzUMXchlpDF87Yhk3bpyvNwWPZT1YPg6j9lNnulq7u/HbNtFpooyENYGL/vJA4GYK0wM5Yp5l2QtWaDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad996dee64a6ae2e9475215fa49415820ba0224d77716d04465b15fc13b451c7","last_reissued_at":"2026-06-23T01:12:36.365147Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:12:36.365147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NASDAQ: Normalized Observation Space Dynamics-Augmented Q-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"(2) EPFL, (3) Purdue University, China, Jianting Zhang (3), Junyuan Liang (1), Switzerland, USA), Wuhui Chen (1) ((1) Sun Yat-sen University, Xinwei Liu (1), Zicong Hong (2)","submitted_at":"2026-06-19T10:21:04Z","abstract_excerpt":"Augmenting model-free reinforcement learning (RL) with representations learned through observation dynamics prediction (observation-predictive RL) can improve sample efficiency and performance, with minor modifications and limited additional computation. However, this approach still struggles in challenging tasks with low-dimensional observations. In this paper, we identify a key factor behind this problem: unbalanced reconstruction losses across observation dimensions, where dimensions with larger value ranges dominate the loss. This encourages the agent to neglect dimensions with relatively "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21297","kind":"arxiv","version":1},"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/2606.21297/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.21297","created_at":"2026-06-23T01:12:36.365222+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21297v1","created_at":"2026-06-23T01:12:36.365222+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21297","created_at":"2026-06-23T01:12:36.365222+00:00"},{"alias_kind":"pith_short_12","alias_value":"VWMW33TEU2XC","created_at":"2026-06-23T01:12:36.365222+00:00"},{"alias_kind":"pith_short_16","alias_value":"VWMW33TEU2XC5FDV","created_at":"2026-06-23T01:12:36.365222+00:00"},{"alias_kind":"pith_short_8","alias_value":"VWMW33TE","created_at":"2026-06-23T01:12:36.365222+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VWMW33TEU2XC5FDVEFP2JFAVQI","json":"https://pith.science/pith/VWMW33TEU2XC5FDVEFP2JFAVQI.json","graph_json":"https://pith.science/api/pith-number/VWMW33TEU2XC5FDVEFP2JFAVQI/graph.json","events_json":"https://pith.science/api/pith-number/VWMW33TEU2XC5FDVEFP2JFAVQI/events.json","paper":"https://pith.science/paper/VWMW33TE"},"agent_actions":{"view_html":"https://pith.science/pith/VWMW33TEU2XC5FDVEFP2JFAVQI","download_json":"https://pith.science/pith/VWMW33TEU2XC5FDVEFP2JFAVQI.json","view_paper":"https://pith.science/paper/VWMW33TE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21297&json=true","fetch_graph":"https://pith.science/api/pith-number/VWMW33TEU2XC5FDVEFP2JFAVQI/graph.json","fetch_events":"https://pith.science/api/pith-number/VWMW33TEU2XC5FDVEFP2JFAVQI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VWMW33TEU2XC5FDVEFP2JFAVQI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VWMW33TEU2XC5FDVEFP2JFAVQI/action/storage_attestation","attest_author":"https://pith.science/pith/VWMW33TEU2XC5FDVEFP2JFAVQI/action/author_attestation","sign_citation":"https://pith.science/pith/VWMW33TEU2XC5FDVEFP2JFAVQI/action/citation_signature","submit_replication":"https://pith.science/pith/VWMW33TEU2XC5FDVEFP2JFAVQI/action/replication_record"}},"created_at":"2026-06-23T01:12:36.365222+00:00","updated_at":"2026-06-23T01:12:36.365222+00:00"}