{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ZZGYJFHAAS43ROVISSZ5XUTGND","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":"b8f90a0f6922c89ee19ef8963de56954282b6a7e335da1a1077f7abd78d173fc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-29T02:29:32Z","title_canon_sha256":"298b6a7ffe1ac1522954c01ff0de9e89e036bd3fb5189fcf5e7fe5a6f6827ab6"},"schema_version":"1.0","source":{"id":"2205.14557","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.14557","created_at":"2026-07-05T06:03:24Z"},{"alias_kind":"arxiv_version","alias_value":"2205.14557v2","created_at":"2026-07-05T06:03:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14557","created_at":"2026-07-05T06:03:24Z"},{"alias_kind":"pith_short_12","alias_value":"ZZGYJFHAAS43","created_at":"2026-07-05T06:03:24Z"},{"alias_kind":"pith_short_16","alias_value":"ZZGYJFHAAS43ROVI","created_at":"2026-07-05T06:03:24Z"},{"alias_kind":"pith_short_8","alias_value":"ZZGYJFHA","created_at":"2026-07-05T06:03:24Z"}],"graph_snapshots":[{"event_id":"sha256:930877581c9b89624f604b50e312c953e86793a43fbbdb158be4b7031e910cb4","target":"graph","created_at":"2026-07-05T06:03:24Z","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/2205.14557/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning (DRL) gives the promise that an agent learns good policy from high-dimensional information, whereas representation learning removes irrelevant and redundant information and retains pertinent information. In this work, we demonstrate that the learned representation of the $Q$-network and its target $Q$-network should, in theory, satisfy a favorable distinguishable representation property. Specifically, there exists an upper bound on the representation similarity of the value functions of two adjacent time steps in a typical DRL setting. However, through illustrative ","authors_text":"Huangyuan Su, Jieyu Zhang, Qiang He, Xinwen Hou","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-29T02:29:32Z","title":"Frustratingly Easy Regularization on Representation Can Boost Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14557","kind":"arxiv","version":2},"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":"sha256:349f0b12866cee0f2a3f6c442f843824aea0170391779b486af01d9ae67a413d","target":"record","created_at":"2026-07-05T06:03:24Z","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":"b8f90a0f6922c89ee19ef8963de56954282b6a7e335da1a1077f7abd78d173fc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-29T02:29:32Z","title_canon_sha256":"298b6a7ffe1ac1522954c01ff0de9e89e036bd3fb5189fcf5e7fe5a6f6827ab6"},"schema_version":"1.0","source":{"id":"2205.14557","kind":"arxiv","version":2}},"canonical_sha256":"ce4d8494e004b9b8baa894b3dbd26668ded9d7b5d63f9e63d819b237561828b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce4d8494e004b9b8baa894b3dbd26668ded9d7b5d63f9e63d819b237561828b4","first_computed_at":"2026-07-05T06:03:24.153806Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:03:24.153806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Bg+u4O0k2bgqjGM/xs8VyztMYYJNpUrICIpb4fQR2blIYTrp5CXe9XfWaednwZTp5JNlUnHCYKAJfXxzFnlWAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:03:24.154205Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.14557","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:349f0b12866cee0f2a3f6c442f843824aea0170391779b486af01d9ae67a413d","sha256:930877581c9b89624f604b50e312c953e86793a43fbbdb158be4b7031e910cb4"],"state_sha256":"aafd79aa9aa5e730f2be2c8c6e92d4df2afa284832d255187d5f4733da6c7c91"}