{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:YI72OG3OBIHGCF22JACA6TVHNS","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":"01d8cf836588273a42ad3b4dd19e0b1f480b5096fb30dc81d15951e0ec42bbfe","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-12T17:57:02Z","title_canon_sha256":"fee6388979ece2453baf5a268b79ce7f3a63cf908eb36b3c08794dc2d391fcb5"},"schema_version":"1.0","source":{"id":"1906.05274","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.05274","created_at":"2026-07-05T00:44:25Z"},{"alias_kind":"arxiv_version","alias_value":"1906.05274v3","created_at":"2026-07-05T00:44:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05274","created_at":"2026-07-05T00:44:25Z"},{"alias_kind":"pith_short_12","alias_value":"YI72OG3OBIHG","created_at":"2026-07-05T00:44:25Z"},{"alias_kind":"pith_short_16","alias_value":"YI72OG3OBIHGCF22","created_at":"2026-07-05T00:44:25Z"},{"alias_kind":"pith_short_8","alias_value":"YI72OG3O","created_at":"2026-07-05T00:44:25Z"}],"graph_snapshots":[{"event_id":"sha256:c9da49ea3cd7f7bf88296a5ae589e407a08e3eb12c2f3576ea0b03567a192b38","target":"graph","created_at":"2026-07-05T00:44:25Z","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/1906.05274/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Benjamin Eysenbach, Emilio Parisotto, Eric Xing, Lisa Lee, Ruslan Salakhutdinov, Sergey Levine","cross_cats":["cs.AI","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-12T17:57:02Z","title":"Efficient Exploration via State Marginal Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05274","kind":"arxiv","version":3},"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":"sha256:8276808758ccc123587a15a6e65ca2df5761f4f9a3e9afd4acd5f09079467ca1","target":"record","created_at":"2026-07-05T00:44:25Z","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":"01d8cf836588273a42ad3b4dd19e0b1f480b5096fb30dc81d15951e0ec42bbfe","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-12T17:57:02Z","title_canon_sha256":"fee6388979ece2453baf5a268b79ce7f3a63cf908eb36b3c08794dc2d391fcb5"},"schema_version":"1.0","source":{"id":"1906.05274","kind":"arxiv","version":3}},"canonical_sha256":"c23fa71b6e0a0e61175a48040f4ea76c93050eb96893610e6cdf42d817da27a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c23fa71b6e0a0e61175a48040f4ea76c93050eb96893610e6cdf42d817da27a6","first_computed_at":"2026-07-05T00:44:25.890017Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:44:25.890017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AmvcgGER1p8inD5VVpsSPkk7G5CroHxIQ0o+s4hkNFH4L6/NgRheoUNDS1SEZcIr+gGLCraoZssqEFqAOcpzDA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:44:25.890459Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.05274","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8276808758ccc123587a15a6e65ca2df5761f4f9a3e9afd4acd5f09079467ca1","sha256:c9da49ea3cd7f7bf88296a5ae589e407a08e3eb12c2f3576ea0b03567a192b38"],"state_sha256":"99c8d5175e786323df61130d78187149798029b2fde5213beb9220b3093be9ca"}