{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:YI72OG3OBIHGCF22JACA6TVHNS","short_pith_number":"pith:YI72OG3O","schema_version":"1.0","canonical_sha256":"c23fa71b6e0a0e61175a48040f4ea76c93050eb96893610e6cdf42d817da27a6","source":{"kind":"arxiv","id":"1906.05274","version":3},"attestation_state":"computed","paper":{"title":"Efficient Exploration via State Marginal Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Benjamin Eysenbach, Emilio Parisotto, Eric Xing, Lisa Lee, Ruslan Salakhutdinov, Sergey Levine","submitted_at":"2019-06-12T17:57:02Z","abstract_excerpt":"Exploration is critical to a reinforcement learning agent's performance in its given environment. Prior exploration methods are often based on using heuristic auxiliary predictions to guide policy behavior, lacking a mathematically-grounded objective with clear properties. In contrast, we recast exploration as a problem of State Marginal Matching (SMM), where we aim to learn a policy for which the state marginal distribution matches a given target state distribution. The target distribution is a uniform distribution in most cases, but can incorporate prior knowledge if available. In effect, SM"},"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":"1906.05274","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-12T17:57:02Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"fee6388979ece2453baf5a268b79ce7f3a63cf908eb36b3c08794dc2d391fcb5","abstract_canon_sha256":"01d8cf836588273a42ad3b4dd19e0b1f480b5096fb30dc81d15951e0ec42bbfe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:44:25.890459Z","signature_b64":"AmvcgGER1p8inD5VVpsSPkk7G5CroHxIQ0o+s4hkNFH4L6/NgRheoUNDS1SEZcIr+gGLCraoZssqEFqAOcpzDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c23fa71b6e0a0e61175a48040f4ea76c93050eb96893610e6cdf42d817da27a6","last_reissued_at":"2026-07-05T00:44:25.890017Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:44:25.890017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Exploration via State Marginal Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Benjamin Eysenbach, Emilio Parisotto, Eric Xing, Lisa Lee, Ruslan Salakhutdinov, Sergey Levine","submitted_at":"2019-06-12T17:57:02Z","abstract_excerpt":"Exploration is critical to a reinforcement learning agent's performance in its given environment. Prior exploration methods are often based on using heuristic auxiliary predictions to guide policy behavior, lacking a mathematically-grounded objective with clear properties. In contrast, we recast exploration as a problem of State Marginal Matching (SMM), where we aim to learn a policy for which the state marginal distribution matches a given target state distribution. The target distribution is a uniform distribution in most cases, but can incorporate prior knowledge if available. In effect, SM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05274","kind":"arxiv","version":3},"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/1906.05274/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":"1906.05274","created_at":"2026-07-05T00:44:25.890070+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.05274v3","created_at":"2026-07-05T00:44:25.890070+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05274","created_at":"2026-07-05T00:44:25.890070+00:00"},{"alias_kind":"pith_short_12","alias_value":"YI72OG3OBIHG","created_at":"2026-07-05T00:44:25.890070+00:00"},{"alias_kind":"pith_short_16","alias_value":"YI72OG3OBIHGCF22","created_at":"2026-07-05T00:44:25.890070+00:00"},{"alias_kind":"pith_short_8","alias_value":"YI72OG3O","created_at":"2026-07-05T00:44:25.890070+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21271","citing_title":"Reward-free Pretraining for Reinforcement Learning via Occupancy Coverage Maximization","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2506.14648","citing_title":"SENIOR: Efficient Query Selection and Preference-Guided Exploration in Preference-based Reinforcement Learning","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01862","citing_title":"QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL","ref_index":102,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05931","citing_title":"Saliency-Guided Representation with Consistency Policy Learning for Visual Unsupervised Reinforcement Learning","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YI72OG3OBIHGCF22JACA6TVHNS","json":"https://pith.science/pith/YI72OG3OBIHGCF22JACA6TVHNS.json","graph_json":"https://pith.science/api/pith-number/YI72OG3OBIHGCF22JACA6TVHNS/graph.json","events_json":"https://pith.science/api/pith-number/YI72OG3OBIHGCF22JACA6TVHNS/events.json","paper":"https://pith.science/paper/YI72OG3O"},"agent_actions":{"view_html":"https://pith.science/pith/YI72OG3OBIHGCF22JACA6TVHNS","download_json":"https://pith.science/pith/YI72OG3OBIHGCF22JACA6TVHNS.json","view_paper":"https://pith.science/paper/YI72OG3O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.05274&json=true","fetch_graph":"https://pith.science/api/pith-number/YI72OG3OBIHGCF22JACA6TVHNS/graph.json","fetch_events":"https://pith.science/api/pith-number/YI72OG3OBIHGCF22JACA6TVHNS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YI72OG3OBIHGCF22JACA6TVHNS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YI72OG3OBIHGCF22JACA6TVHNS/action/storage_attestation","attest_author":"https://pith.science/pith/YI72OG3OBIHGCF22JACA6TVHNS/action/author_attestation","sign_citation":"https://pith.science/pith/YI72OG3OBIHGCF22JACA6TVHNS/action/citation_signature","submit_replication":"https://pith.science/pith/YI72OG3OBIHGCF22JACA6TVHNS/action/replication_record"}},"created_at":"2026-07-05T00:44:25.890070+00:00","updated_at":"2026-07-05T00:44:25.890070+00:00"}