{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:23YGPHAVLXJK4EAIRVIAKQ7Y55","short_pith_number":"pith:23YGPHAV","schema_version":"1.0","canonical_sha256":"d6f0679c155dd2ae10088d500543f8ef499019797e54772e4f07e21cf43af67f","source":{"kind":"arxiv","id":"2310.07518","version":2},"attestation_state":"computed","paper":{"title":"Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Marx, Giorgia Ramponi, Marcello Restelli, Mirco Mutti, Riccardo De Santi","submitted_at":"2023-10-11T14:16:04Z","abstract_excerpt":"Posterior sampling allows exploitation of prior knowledge on the environment's transition dynamics to improve the sample efficiency of reinforcement learning. The prior is typically specified as a class of parametric distributions, the design of which can be cumbersome in practice, often resulting in the choice of uninformative priors. In this work, we propose a novel posterior sampling approach in which the prior is given as a (partial) causal graph over the environment's variables. The latter is often more natural to design, such as listing known causal dependencies between biometric feature"},"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":"2310.07518","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-11T14:16:04Z","cross_cats_sorted":[],"title_canon_sha256":"ace92ed268b30c88b85343cab6ffbcc2067adbac197675e14c327307f3fe4050","abstract_canon_sha256":"e41cacd6906f4832914a5cd3985d33f4d45e7a8b24e9fef80f4bb3e0f438e64f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:03.706468Z","signature_b64":"8nJeA1MCCg2ZC/zAyyud7fywr3zWrkHNcngFTz9btOX4wH7L2/R6r2MMbjs2d+0rAWyORIDMvNP3t3Ta0YDMDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6f0679c155dd2ae10088d500543f8ef499019797e54772e4f07e21cf43af67f","last_reissued_at":"2026-07-05T08:05:03.705982Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:03.705982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Marx, Giorgia Ramponi, Marcello Restelli, Mirco Mutti, Riccardo De Santi","submitted_at":"2023-10-11T14:16:04Z","abstract_excerpt":"Posterior sampling allows exploitation of prior knowledge on the environment's transition dynamics to improve the sample efficiency of reinforcement learning. The prior is typically specified as a class of parametric distributions, the design of which can be cumbersome in practice, often resulting in the choice of uninformative priors. In this work, we propose a novel posterior sampling approach in which the prior is given as a (partial) causal graph over the environment's variables. The latter is often more natural to design, such as listing known causal dependencies between biometric feature"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07518","kind":"arxiv","version":2},"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/2310.07518/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":"2310.07518","created_at":"2026-07-05T08:05:03.706041+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.07518v2","created_at":"2026-07-05T08:05:03.706041+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07518","created_at":"2026-07-05T08:05:03.706041+00:00"},{"alias_kind":"pith_short_12","alias_value":"23YGPHAVLXJK","created_at":"2026-07-05T08:05:03.706041+00:00"},{"alias_kind":"pith_short_16","alias_value":"23YGPHAVLXJK4EAI","created_at":"2026-07-05T08:05:03.706041+00:00"},{"alias_kind":"pith_short_8","alias_value":"23YGPHAV","created_at":"2026-07-05T08:05:03.706041+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.10077","citing_title":"Towards Empowerment Gain through Causal Structure Learning in Model-Based RL","ref_index":2015,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/23YGPHAVLXJK4EAIRVIAKQ7Y55","json":"https://pith.science/pith/23YGPHAVLXJK4EAIRVIAKQ7Y55.json","graph_json":"https://pith.science/api/pith-number/23YGPHAVLXJK4EAIRVIAKQ7Y55/graph.json","events_json":"https://pith.science/api/pith-number/23YGPHAVLXJK4EAIRVIAKQ7Y55/events.json","paper":"https://pith.science/paper/23YGPHAV"},"agent_actions":{"view_html":"https://pith.science/pith/23YGPHAVLXJK4EAIRVIAKQ7Y55","download_json":"https://pith.science/pith/23YGPHAVLXJK4EAIRVIAKQ7Y55.json","view_paper":"https://pith.science/paper/23YGPHAV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.07518&json=true","fetch_graph":"https://pith.science/api/pith-number/23YGPHAVLXJK4EAIRVIAKQ7Y55/graph.json","fetch_events":"https://pith.science/api/pith-number/23YGPHAVLXJK4EAIRVIAKQ7Y55/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/23YGPHAVLXJK4EAIRVIAKQ7Y55/action/timestamp_anchor","attest_storage":"https://pith.science/pith/23YGPHAVLXJK4EAIRVIAKQ7Y55/action/storage_attestation","attest_author":"https://pith.science/pith/23YGPHAVLXJK4EAIRVIAKQ7Y55/action/author_attestation","sign_citation":"https://pith.science/pith/23YGPHAVLXJK4EAIRVIAKQ7Y55/action/citation_signature","submit_replication":"https://pith.science/pith/23YGPHAVLXJK4EAIRVIAKQ7Y55/action/replication_record"}},"created_at":"2026-07-05T08:05:03.706041+00:00","updated_at":"2026-07-05T08:05:03.706041+00:00"}