{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RZ2QLXYFJCEMF77THV763626VA","short_pith_number":"pith:RZ2QLXYF","schema_version":"1.0","canonical_sha256":"8e7505df054888c2fff33d7fedfb5ea83a48048dc9e45e2078c3ed7a6f8b8ede","source":{"kind":"arxiv","id":"2506.17518","version":1},"attestation_state":"computed","paper":{"title":"A Survey of State Representation Learning for Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ayoub Echchahed, Pablo Samuel Castro","submitted_at":"2025-06-20T23:47:04Z","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"},"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":"2506.17518","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-20T23:47:04Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"046db6c7eef9490400b6377f43fedfd6159c1a36a747b374af6e45f9a809ba14","abstract_canon_sha256":"38086089caf33180331cc03f6f774a7e3ddd6eff674eb2e5125d95a563fb3ea9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:18.936978Z","signature_b64":"l0tJYsSh3r/IaF1CtNHkJtfBoqTLDN3PEM2pvXCJ8wjHFMurvRuxyM9YnnuG5Juag1LXOtq+VphfvKk77UksCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e7505df054888c2fff33d7fedfb5ea83a48048dc9e45e2078c3ed7a6f8b8ede","last_reissued_at":"2026-07-05T11:25:18.936474Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:18.936474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey of State Representation Learning for Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ayoub Echchahed, Pablo Samuel Castro","submitted_at":"2025-06-20T23:47:04Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17518","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/2506.17518/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":"2506.17518","created_at":"2026-07-05T11:25:18.936544+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.17518v1","created_at":"2026-07-05T11:25:18.936544+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17518","created_at":"2026-07-05T11:25:18.936544+00:00"},{"alias_kind":"pith_short_12","alias_value":"RZ2QLXYFJCEM","created_at":"2026-07-05T11:25:18.936544+00:00"},{"alias_kind":"pith_short_16","alias_value":"RZ2QLXYFJCEMF77T","created_at":"2026-07-05T11:25:18.936544+00:00"},{"alias_kind":"pith_short_8","alias_value":"RZ2QLXYF","created_at":"2026-07-05T11:25:18.936544+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21943","citing_title":"Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22711","citing_title":"Abstraction for Offline Goal-Conditioned Reinforcement Learning","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09671","citing_title":"Belief-State RWKV for Reinforcement Learning under Partial Observability","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09364","citing_title":"Multi-scale Predictive Representations for Goal-conditioned Reinforcement Learning","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RZ2QLXYFJCEMF77THV763626VA","json":"https://pith.science/pith/RZ2QLXYFJCEMF77THV763626VA.json","graph_json":"https://pith.science/api/pith-number/RZ2QLXYFJCEMF77THV763626VA/graph.json","events_json":"https://pith.science/api/pith-number/RZ2QLXYFJCEMF77THV763626VA/events.json","paper":"https://pith.science/paper/RZ2QLXYF"},"agent_actions":{"view_html":"https://pith.science/pith/RZ2QLXYFJCEMF77THV763626VA","download_json":"https://pith.science/pith/RZ2QLXYFJCEMF77THV763626VA.json","view_paper":"https://pith.science/paper/RZ2QLXYF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.17518&json=true","fetch_graph":"https://pith.science/api/pith-number/RZ2QLXYFJCEMF77THV763626VA/graph.json","fetch_events":"https://pith.science/api/pith-number/RZ2QLXYFJCEMF77THV763626VA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RZ2QLXYFJCEMF77THV763626VA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RZ2QLXYFJCEMF77THV763626VA/action/storage_attestation","attest_author":"https://pith.science/pith/RZ2QLXYFJCEMF77THV763626VA/action/author_attestation","sign_citation":"https://pith.science/pith/RZ2QLXYFJCEMF77THV763626VA/action/citation_signature","submit_replication":"https://pith.science/pith/RZ2QLXYFJCEMF77THV763626VA/action/replication_record"}},"created_at":"2026-07-05T11:25:18.936544+00:00","updated_at":"2026-07-05T11:25:18.936544+00:00"}