{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:X762V5T5FGJIXPMIX5G7HZUXAE","short_pith_number":"pith:X762V5T5","schema_version":"1.0","canonical_sha256":"bffdaaf67d29928bbd88bf4df3e697010fc0cf0747d0a9b5ca6326d69b67f4ad","source":{"kind":"arxiv","id":"2501.09611","version":1},"attestation_state":"computed","paper":{"title":"EVaDE : Event-Based Variational Thompson Sampling for Model-Based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dixant Mittal, Siddharth Aravindan, Wee Sun Lee","submitted_at":"2025-01-16T15:35:48Z","abstract_excerpt":"Posterior Sampling for Reinforcement Learning (PSRL) is a well-known algorithm that augments model-based reinforcement learning (MBRL) algorithms with Thompson sampling. PSRL maintains posterior distributions of the environment transition dynamics and the reward function, which are intractable for tasks with high-dimensional state and action spaces. Recent works show that dropout, used in conjunction with neural networks, induces variational distributions that can approximate these posteriors. In this paper, we propose Event-based Variational Distributions for Exploration (EVaDE), which are va"},"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":"2501.09611","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-16T15:35:48Z","cross_cats_sorted":[],"title_canon_sha256":"7201beff1382352907298597c499b60e91940b3f761ebec1bd1a6b2c35d6e824","abstract_canon_sha256":"ecc3a2140438e8aa2ae73754da46e102c4cb542198ee8b77f6403b0fd2fbd3f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:49.764498Z","signature_b64":"Jqmfz+iRcY7U1JMIj50fok8qW/Qtf55WJbwy7xle3NIj6VgestateTAn5xw2Wqwlr+oJwIo/LQ47e+VCOlZbBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bffdaaf67d29928bbd88bf4df3e697010fc0cf0747d0a9b5ca6326d69b67f4ad","last_reissued_at":"2026-07-05T10:01:49.763954Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:49.763954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EVaDE : Event-Based Variational Thompson Sampling for Model-Based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dixant Mittal, Siddharth Aravindan, Wee Sun Lee","submitted_at":"2025-01-16T15:35:48Z","abstract_excerpt":"Posterior Sampling for Reinforcement Learning (PSRL) is a well-known algorithm that augments model-based reinforcement learning (MBRL) algorithms with Thompson sampling. PSRL maintains posterior distributions of the environment transition dynamics and the reward function, which are intractable for tasks with high-dimensional state and action spaces. Recent works show that dropout, used in conjunction with neural networks, induces variational distributions that can approximate these posteriors. In this paper, we propose Event-based Variational Distributions for Exploration (EVaDE), which are va"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09611","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/2501.09611/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":"2501.09611","created_at":"2026-07-05T10:01:49.764023+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.09611v1","created_at":"2026-07-05T10:01:49.764023+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09611","created_at":"2026-07-05T10:01:49.764023+00:00"},{"alias_kind":"pith_short_12","alias_value":"X762V5T5FGJI","created_at":"2026-07-05T10:01:49.764023+00:00"},{"alias_kind":"pith_short_16","alias_value":"X762V5T5FGJIXPMI","created_at":"2026-07-05T10:01:49.764023+00:00"},{"alias_kind":"pith_short_8","alias_value":"X762V5T5","created_at":"2026-07-05T10:01:49.764023+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X762V5T5FGJIXPMIX5G7HZUXAE","json":"https://pith.science/pith/X762V5T5FGJIXPMIX5G7HZUXAE.json","graph_json":"https://pith.science/api/pith-number/X762V5T5FGJIXPMIX5G7HZUXAE/graph.json","events_json":"https://pith.science/api/pith-number/X762V5T5FGJIXPMIX5G7HZUXAE/events.json","paper":"https://pith.science/paper/X762V5T5"},"agent_actions":{"view_html":"https://pith.science/pith/X762V5T5FGJIXPMIX5G7HZUXAE","download_json":"https://pith.science/pith/X762V5T5FGJIXPMIX5G7HZUXAE.json","view_paper":"https://pith.science/paper/X762V5T5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.09611&json=true","fetch_graph":"https://pith.science/api/pith-number/X762V5T5FGJIXPMIX5G7HZUXAE/graph.json","fetch_events":"https://pith.science/api/pith-number/X762V5T5FGJIXPMIX5G7HZUXAE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X762V5T5FGJIXPMIX5G7HZUXAE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X762V5T5FGJIXPMIX5G7HZUXAE/action/storage_attestation","attest_author":"https://pith.science/pith/X762V5T5FGJIXPMIX5G7HZUXAE/action/author_attestation","sign_citation":"https://pith.science/pith/X762V5T5FGJIXPMIX5G7HZUXAE/action/citation_signature","submit_replication":"https://pith.science/pith/X762V5T5FGJIXPMIX5G7HZUXAE/action/replication_record"}},"created_at":"2026-07-05T10:01:49.764023+00:00","updated_at":"2026-07-05T10:01:49.764023+00:00"}