{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KPUQRCQTBEIGYIK3LPA33JTTYT","short_pith_number":"pith:KPUQRCQT","schema_version":"1.0","canonical_sha256":"53e9088a1309106c215b5bc1bda673c4d0a3150d9fb174b7813b43ad687f1853","source":{"kind":"arxiv","id":"2102.09225","version":4},"attestation_state":"computed","paper":{"title":"Continuous Doubly Constrained Batch Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander J. Smola, Jonas Mueller, Kavosh Asadi, Pratik Chaudhari, Rasool Fakoor","submitted_at":"2021-02-18T08:54:14Z","abstract_excerpt":"Reliant on too many experiments to learn good actions, current Reinforcement Learning (RL) algorithms have limited applicability in real-world settings, which can be too expensive to allow exploration. We propose an algorithm for batch RL, where effective policies are learned using only a fixed offline dataset instead of online interactions with the environment. The limited data in batch RL produces inherent uncertainty in value estimates of states/actions that were insufficiently represented in the training data. This leads to particularly severe extrapolation when our candidate policies dive"},"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":"2102.09225","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-18T08:54:14Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a8c230c765a020484977719d5fd09fc87a46fc8df5b09cc8df2fd65fbd3f6e2d","abstract_canon_sha256":"b515fd128856e0d2421938b55517d43c92cc80ed24cb1afccef65caa3d9d6e93"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:37:40.772184Z","signature_b64":"dT/VKEO/mmNVAWzPm4fWBL/mzHR3otESQxRV6tpsH1fi/oOSELT6EPQKW+BvBQjSsS32CtMQlBa+LuoIIjdrBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53e9088a1309106c215b5bc1bda673c4d0a3150d9fb174b7813b43ad687f1853","last_reissued_at":"2026-07-05T03:37:40.771667Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:37:40.771667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continuous Doubly Constrained Batch Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander J. Smola, Jonas Mueller, Kavosh Asadi, Pratik Chaudhari, Rasool Fakoor","submitted_at":"2021-02-18T08:54:14Z","abstract_excerpt":"Reliant on too many experiments to learn good actions, current Reinforcement Learning (RL) algorithms have limited applicability in real-world settings, which can be too expensive to allow exploration. We propose an algorithm for batch RL, where effective policies are learned using only a fixed offline dataset instead of online interactions with the environment. The limited data in batch RL produces inherent uncertainty in value estimates of states/actions that were insufficiently represented in the training data. This leads to particularly severe extrapolation when our candidate policies dive"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.09225","kind":"arxiv","version":4},"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/2102.09225/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":"2102.09225","created_at":"2026-07-05T03:37:40.771739+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.09225v4","created_at":"2026-07-05T03:37:40.771739+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.09225","created_at":"2026-07-05T03:37:40.771739+00:00"},{"alias_kind":"pith_short_12","alias_value":"KPUQRCQTBEIG","created_at":"2026-07-05T03:37:40.771739+00:00"},{"alias_kind":"pith_short_16","alias_value":"KPUQRCQTBEIGYIK3","created_at":"2026-07-05T03:37:40.771739+00:00"},{"alias_kind":"pith_short_8","alias_value":"KPUQRCQT","created_at":"2026-07-05T03:37:40.771739+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/KPUQRCQTBEIGYIK3LPA33JTTYT","json":"https://pith.science/pith/KPUQRCQTBEIGYIK3LPA33JTTYT.json","graph_json":"https://pith.science/api/pith-number/KPUQRCQTBEIGYIK3LPA33JTTYT/graph.json","events_json":"https://pith.science/api/pith-number/KPUQRCQTBEIGYIK3LPA33JTTYT/events.json","paper":"https://pith.science/paper/KPUQRCQT"},"agent_actions":{"view_html":"https://pith.science/pith/KPUQRCQTBEIGYIK3LPA33JTTYT","download_json":"https://pith.science/pith/KPUQRCQTBEIGYIK3LPA33JTTYT.json","view_paper":"https://pith.science/paper/KPUQRCQT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.09225&json=true","fetch_graph":"https://pith.science/api/pith-number/KPUQRCQTBEIGYIK3LPA33JTTYT/graph.json","fetch_events":"https://pith.science/api/pith-number/KPUQRCQTBEIGYIK3LPA33JTTYT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KPUQRCQTBEIGYIK3LPA33JTTYT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KPUQRCQTBEIGYIK3LPA33JTTYT/action/storage_attestation","attest_author":"https://pith.science/pith/KPUQRCQTBEIGYIK3LPA33JTTYT/action/author_attestation","sign_citation":"https://pith.science/pith/KPUQRCQTBEIGYIK3LPA33JTTYT/action/citation_signature","submit_replication":"https://pith.science/pith/KPUQRCQTBEIGYIK3LPA33JTTYT/action/replication_record"}},"created_at":"2026-07-05T03:37:40.771739+00:00","updated_at":"2026-07-05T03:37:40.771739+00:00"}