{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RZ2QLXYFJCEMF77THV763626VA","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":"38086089caf33180331cc03f6f774a7e3ddd6eff674eb2e5125d95a563fb3ea9","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-20T23:47:04Z","title_canon_sha256":"046db6c7eef9490400b6377f43fedfd6159c1a36a747b374af6e45f9a809ba14"},"schema_version":"1.0","source":{"id":"2506.17518","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.17518","created_at":"2026-07-05T11:25:18Z"},{"alias_kind":"arxiv_version","alias_value":"2506.17518v1","created_at":"2026-07-05T11:25:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17518","created_at":"2026-07-05T11:25:18Z"},{"alias_kind":"pith_short_12","alias_value":"RZ2QLXYFJCEM","created_at":"2026-07-05T11:25:18Z"},{"alias_kind":"pith_short_16","alias_value":"RZ2QLXYFJCEMF77T","created_at":"2026-07-05T11:25:18Z"},{"alias_kind":"pith_short_8","alias_value":"RZ2QLXYF","created_at":"2026-07-05T11:25:18Z"}],"graph_snapshots":[{"event_id":"sha256:0e395880632dbe20cfed6e94789c517b5ceaaa9ac2d38a1a90a63ae93d25cdd0","target":"graph","created_at":"2026-07-05T11:25:18Z","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/2506.17518/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Representation learning methods are an important tool for addressing the challenges posed by complex observations spaces in sequential decision making problems. Recently, many methods have used a wide variety of types of approaches for learning meaningful state representations in reinforcement learning, allowing better sample efficiency, generalization, and performance. This survey aims to provide a broad categorization of these methods within a model-free online setting, exploring how they tackle the learning of state representations differently. We categorize the methods into six main classe","authors_text":"Ayoub Echchahed, Pablo Samuel Castro","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-20T23:47:04Z","title":"A Survey of State Representation Learning for Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17518","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:dc01db93ff4b26ab36015801c3b3c1be42cd46fc87ad5695edb5cc7c1b6a9a00","target":"record","created_at":"2026-07-05T11:25:18Z","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":"38086089caf33180331cc03f6f774a7e3ddd6eff674eb2e5125d95a563fb3ea9","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-20T23:47:04Z","title_canon_sha256":"046db6c7eef9490400b6377f43fedfd6159c1a36a747b374af6e45f9a809ba14"},"schema_version":"1.0","source":{"id":"2506.17518","kind":"arxiv","version":1}},"canonical_sha256":"8e7505df054888c2fff33d7fedfb5ea83a48048dc9e45e2078c3ed7a6f8b8ede","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e7505df054888c2fff33d7fedfb5ea83a48048dc9e45e2078c3ed7a6f8b8ede","first_computed_at":"2026-07-05T11:25:18.936474Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:18.936474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l0tJYsSh3r/IaF1CtNHkJtfBoqTLDN3PEM2pvXCJ8wjHFMurvRuxyM9YnnuG5Juag1LXOtq+VphfvKk77UksCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:18.936978Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.17518","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc01db93ff4b26ab36015801c3b3c1be42cd46fc87ad5695edb5cc7c1b6a9a00","sha256:0e395880632dbe20cfed6e94789c517b5ceaaa9ac2d38a1a90a63ae93d25cdd0"],"state_sha256":"ec48abb0747fa5303b1fa9975ce3a8f16ec882867ebd1bcc2c069c1fd6d5f561"}