{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:7MIGKFK2X522WQ6UOLSH6RVQUL","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":"030188761cc46b4973fd72d25c0ac9cf9d86d5f57202c37c4c7f6844ef3ded74","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-06T12:09:18Z","title_canon_sha256":"5055960679ae15bd94f4277c1bd8612f85d3d833157a794a6ffb763608c77ae0"},"schema_version":"1.0","source":{"id":"2008.02598","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.02598","created_at":"2026-07-05T02:14:42Z"},{"alias_kind":"arxiv_version","alias_value":"2008.02598v3","created_at":"2026-07-05T02:14:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.02598","created_at":"2026-07-05T02:14:42Z"},{"alias_kind":"pith_short_12","alias_value":"7MIGKFK2X522","created_at":"2026-07-05T02:14:42Z"},{"alias_kind":"pith_short_16","alias_value":"7MIGKFK2X522WQ6U","created_at":"2026-07-05T02:14:42Z"},{"alias_kind":"pith_short_8","alias_value":"7MIGKFK2","created_at":"2026-07-05T02:14:42Z"}],"graph_snapshots":[{"event_id":"sha256:f59b198657122cf553a2b8b7275d539df6f483525d9ba213cbbc60764a28acf8","target":"graph","created_at":"2026-07-05T02:14:42Z","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/2008.02598/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Consider the following instance of the Offline Meta Reinforcement Learning (OMRL) problem: given the complete training logs of $N$ conventional RL agents, trained on $N$ different tasks, design a meta-agent that can quickly maximize reward in a new, unseen task from the same task distribution. In particular, while each conventional RL agent explored and exploited its own different task, the meta-agent must identify regularities in the data that lead to effective exploration/exploitation in the unseen task. Here, we take a Bayesian RL (BRL) view, and seek to learn a Bayes-optimal policy from th","authors_text":"Aviv Tamar, Idan Shenfeld, Ron Dorfman","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-06T12:09:18Z","title":"Offline Meta Learning of Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.02598","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":"sha256:933826b3d72cad900b5ff2ecc7aa60815f1a50dbdcf64322497e4500b6dcc94a","target":"record","created_at":"2026-07-05T02:14:42Z","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":"030188761cc46b4973fd72d25c0ac9cf9d86d5f57202c37c4c7f6844ef3ded74","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-06T12:09:18Z","title_canon_sha256":"5055960679ae15bd94f4277c1bd8612f85d3d833157a794a6ffb763608c77ae0"},"schema_version":"1.0","source":{"id":"2008.02598","kind":"arxiv","version":3}},"canonical_sha256":"fb1065155abf75ab43d472e47f46b0a2e81b5644b6af3838f698e823fb78a062","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb1065155abf75ab43d472e47f46b0a2e81b5644b6af3838f698e823fb78a062","first_computed_at":"2026-07-05T02:14:42.809681Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:14:42.809681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"twg6ulUW/f/BbxDh0OrBgH25L4HaIBN0b/tfI5P2RpTHnWdbrqzlBKmBdkOQKLr1t5ud+Qwrfnfjc+ZcbZahBA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:14:42.810133Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.02598","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:933826b3d72cad900b5ff2ecc7aa60815f1a50dbdcf64322497e4500b6dcc94a","sha256:f59b198657122cf553a2b8b7275d539df6f483525d9ba213cbbc60764a28acf8"],"state_sha256":"74c166416c87c7f8866d3d61bc5790fe09c645cd5f14c3d15291bab93c473aaa"}