{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:PTKTTPGW53MGFI37SKPDS6C6TR","short_pith_number":"pith:PTKTTPGW","canonical_record":{"source":{"id":"1812.02900","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-07T04:03:25Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"09e5c062f10a2b8eee3af2580104024c7effcfa6441fe97bac903f6ad8816e6b","abstract_canon_sha256":"82f140ea63edc590404df5d8aae083eca4778dab010521478691b1c401fb299c"},"schema_version":"1.0"},"canonical_sha256":"7cd539bcd6eed862a37f929e39785e9c696c456ebae26f8239e27d21256e50cf","source":{"kind":"arxiv","id":"1812.02900","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.02900","created_at":"2026-07-04T23:53:11Z"},{"alias_kind":"arxiv_version","alias_value":"1812.02900v3","created_at":"2026-07-04T23:53:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.02900","created_at":"2026-07-04T23:53:11Z"},{"alias_kind":"pith_short_12","alias_value":"PTKTTPGW53MG","created_at":"2026-07-04T23:53:11Z"},{"alias_kind":"pith_short_16","alias_value":"PTKTTPGW53MGFI37","created_at":"2026-07-04T23:53:11Z"},{"alias_kind":"pith_short_8","alias_value":"PTKTTPGW","created_at":"2026-07-04T23:53:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:PTKTTPGW53MGFI37SKPDS6C6TR","target":"record","payload":{"canonical_record":{"source":{"id":"1812.02900","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-07T04:03:25Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"09e5c062f10a2b8eee3af2580104024c7effcfa6441fe97bac903f6ad8816e6b","abstract_canon_sha256":"82f140ea63edc590404df5d8aae083eca4778dab010521478691b1c401fb299c"},"schema_version":"1.0"},"canonical_sha256":"7cd539bcd6eed862a37f929e39785e9c696c456ebae26f8239e27d21256e50cf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:53:11.089210Z","signature_b64":"UAtwFcvVJRdvBUisIqTDa6nNfJpiEJOc9e1o1yLtbodazhNEdL8w09GAV0DfRFc9plp8UH+VfueI1xAZgVgRDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cd539bcd6eed862a37f929e39785e9c696c456ebae26f8239e27d21256e50cf","last_reissued_at":"2026-07-04T23:53:11.088824Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:53:11.088824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.02900","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T23:53:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jbfFG11LX0S9lVeYDbuAITHpS9V7bkJY31z43qrjZmFxZ6EAxMXcDINpPtGA6ZHtYUGrASJM0gkrJ7u8pCssCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T19:56:58.307828Z"},"content_sha256":"9c220ed029f0c08e09bee12fea66a8e271bf3a3a9507f58b15742bb0929cb5da","schema_version":"1.0","event_id":"sha256:9c220ed029f0c08e09bee12fea66a8e271bf3a3a9507f58b15742bb0929cb5da"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:PTKTTPGW53MGFI37SKPDS6C6TR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Off-Policy Deep Reinforcement Learning without Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Meger, Doina Precup, Scott Fujimoto","submitted_at":"2018-12-07T04:03:25Z","abstract_excerpt":"Many practical applications of reinforcement learning constrain agents to learn from a fixed batch of data which has already been gathered, without offering further possibility for data collection. In this paper, we demonstrate that due to errors introduced by extrapolation, standard off-policy deep reinforcement learning algorithms, such as DQN and DDPG, are incapable of learning with data uncorrelated to the distribution under the current policy, making them ineffective for this fixed batch setting. We introduce a novel class of off-policy algorithms, batch-constrained reinforcement learning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.02900","kind":"arxiv","version":3},"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/1812.02900/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T23:53:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d6b6B1mc10smZcX8MK2Z9rNDDGu4LNdg8XmTq64lcUjgTOW7lLZh8kjwxpke46xRNZXEOsJvFK0CkbsDAeLtBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T19:56:58.308704Z"},"content_sha256":"ea4fb3f7631daf29ef66136b616301fcbabb501aa6231cc7065139bf66aca622","schema_version":"1.0","event_id":"sha256:ea4fb3f7631daf29ef66136b616301fcbabb501aa6231cc7065139bf66aca622"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PTKTTPGW53MGFI37SKPDS6C6TR/bundle.json","state_url":"https://pith.science/pith/PTKTTPGW53MGFI37SKPDS6C6TR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PTKTTPGW53MGFI37SKPDS6C6TR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-21T19:56:58Z","links":{"resolver":"https://pith.science/pith/PTKTTPGW53MGFI37SKPDS6C6TR","bundle":"https://pith.science/pith/PTKTTPGW53MGFI37SKPDS6C6TR/bundle.json","state":"https://pith.science/pith/PTKTTPGW53MGFI37SKPDS6C6TR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PTKTTPGW53MGFI37SKPDS6C6TR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:PTKTTPGW53MGFI37SKPDS6C6TR","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":"82f140ea63edc590404df5d8aae083eca4778dab010521478691b1c401fb299c","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-07T04:03:25Z","title_canon_sha256":"09e5c062f10a2b8eee3af2580104024c7effcfa6441fe97bac903f6ad8816e6b"},"schema_version":"1.0","source":{"id":"1812.02900","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.02900","created_at":"2026-07-04T23:53:11Z"},{"alias_kind":"arxiv_version","alias_value":"1812.02900v3","created_at":"2026-07-04T23:53:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.02900","created_at":"2026-07-04T23:53:11Z"},{"alias_kind":"pith_short_12","alias_value":"PTKTTPGW53MG","created_at":"2026-07-04T23:53:11Z"},{"alias_kind":"pith_short_16","alias_value":"PTKTTPGW53MGFI37","created_at":"2026-07-04T23:53:11Z"},{"alias_kind":"pith_short_8","alias_value":"PTKTTPGW","created_at":"2026-07-04T23:53:11Z"}],"graph_snapshots":[{"event_id":"sha256:ea4fb3f7631daf29ef66136b616301fcbabb501aa6231cc7065139bf66aca622","target":"graph","created_at":"2026-07-04T23:53:11Z","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/1812.02900/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many practical applications of reinforcement learning constrain agents to learn from a fixed batch of data which has already been gathered, without offering further possibility for data collection. In this paper, we demonstrate that due to errors introduced by extrapolation, standard off-policy deep reinforcement learning algorithms, such as DQN and DDPG, are incapable of learning with data uncorrelated to the distribution under the current policy, making them ineffective for this fixed batch setting. We introduce a novel class of off-policy algorithms, batch-constrained reinforcement learning","authors_text":"David Meger, Doina Precup, Scott Fujimoto","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-07T04:03:25Z","title":"Off-Policy Deep Reinforcement Learning without Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.02900","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":"sha256:9c220ed029f0c08e09bee12fea66a8e271bf3a3a9507f58b15742bb0929cb5da","target":"record","created_at":"2026-07-04T23:53:11Z","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":"82f140ea63edc590404df5d8aae083eca4778dab010521478691b1c401fb299c","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-07T04:03:25Z","title_canon_sha256":"09e5c062f10a2b8eee3af2580104024c7effcfa6441fe97bac903f6ad8816e6b"},"schema_version":"1.0","source":{"id":"1812.02900","kind":"arxiv","version":3}},"canonical_sha256":"7cd539bcd6eed862a37f929e39785e9c696c456ebae26f8239e27d21256e50cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7cd539bcd6eed862a37f929e39785e9c696c456ebae26f8239e27d21256e50cf","first_computed_at":"2026-07-04T23:53:11.088824Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:53:11.088824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UAtwFcvVJRdvBUisIqTDa6nNfJpiEJOc9e1o1yLtbodazhNEdL8w09GAV0DfRFc9plp8UH+VfueI1xAZgVgRDg==","signature_status":"signed_v1","signed_at":"2026-07-04T23:53:11.089210Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.02900","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c220ed029f0c08e09bee12fea66a8e271bf3a3a9507f58b15742bb0929cb5da","sha256:ea4fb3f7631daf29ef66136b616301fcbabb501aa6231cc7065139bf66aca622"],"state_sha256":"4d7d3122deeeb4aee28a9a71e0937b11269744ab6d0bfedd22c3fb3af06ba174"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x5DmY15uEJ/6wyRXhos2apq3L6Mp+V/v3XgjwuZ6JXdMY2+cD28WbqDJGd/kpm1RWFXZCST4BVqtu3fL35QyCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T19:56:58.383339Z","bundle_sha256":"60d5c812b6bdcfc7189caa1493d14789959c6ef09931494ed5c2b06bd75b23f7"}}