{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:IATTN4REXT4GBU4BYFHGNOGDVO","short_pith_number":"pith:IATTN4RE","canonical_record":{"source":{"id":"1909.01387","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-03T18:20:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b388e9874d112092568ec6f2a7fc2dbf7d9bb10506ea9b0f8cee2f441dc11a20","abstract_canon_sha256":"9cb0a79cef24d4680b0d12d55878f7307e01c482615e4357fe437c8723b467c4"},"schema_version":"1.0"},"canonical_sha256":"402736f224bcf860d381c14e66b8c3abb34e929f3c42589131cd6984365523c3","source":{"kind":"arxiv","id":"1909.01387","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.01387","created_at":"2026-07-05T00:02:15Z"},{"alias_kind":"arxiv_version","alias_value":"1909.01387v1","created_at":"2026-07-05T00:02:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.01387","created_at":"2026-07-05T00:02:15Z"},{"alias_kind":"pith_short_12","alias_value":"IATTN4REXT4G","created_at":"2026-07-05T00:02:15Z"},{"alias_kind":"pith_short_16","alias_value":"IATTN4REXT4GBU4B","created_at":"2026-07-05T00:02:15Z"},{"alias_kind":"pith_short_8","alias_value":"IATTN4RE","created_at":"2026-07-05T00:02:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:IATTN4REXT4GBU4BYFHGNOGDVO","target":"record","payload":{"canonical_record":{"source":{"id":"1909.01387","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-03T18:20:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b388e9874d112092568ec6f2a7fc2dbf7d9bb10506ea9b0f8cee2f441dc11a20","abstract_canon_sha256":"9cb0a79cef24d4680b0d12d55878f7307e01c482615e4357fe437c8723b467c4"},"schema_version":"1.0"},"canonical_sha256":"402736f224bcf860d381c14e66b8c3abb34e929f3c42589131cd6984365523c3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:02:15.681068Z","signature_b64":"QOtkP9WxZgmC92vx1gd1+pM4G1DXrXfX8kkZTRpmw8UpuKxU+oLLbrWOBa4U5vFuwrsEMokudxE5UxxriqC/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"402736f224bcf860d381c14e66b8c3abb34e929f3c42589131cd6984365523c3","last_reissued_at":"2026-07-05T00:02:15.680592Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:02:15.680592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.01387","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:02:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nwv19jt/TRe8XMnV4L3VqtJN2OYZV1+1usuX/9I22agRoybJkuCi9YDaVoFjejouZoIVzCW4/LbB4Z4uHb9iBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:57:18.720432Z"},"content_sha256":"fb57fd3e351447100471a7a04327957a025a821cb5f3ec87c1c66ca5b9cbc0af","schema_version":"1.0","event_id":"sha256:fb57fd3e351447100471a7a04327957a025a821cb5f3ec87c1c66ca5b9cbc0af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:IATTN4REXT4GBU4BYFHGNOGDVO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Making Efficient Use of Demonstrations to Solve Hard Exploration Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bobak Shahriari, Caglar Gulcehre, Duncan Williams, Gabriel Barth-Maron, Hubert Soyer, Matt Hoffman, Misha Denil, Nando de Freitas, Neil Rabinowitz, Richard Tanburn, Steven Kapturowski, Tom Le Paine, Worlds Team, Ziyu Wang","submitted_at":"2019-09-03T18:20:48Z","abstract_excerpt":"This paper introduces R2D3, an agent that makes efficient use of demonstrations to solve hard exploration problems in partially observable environments with highly variable initial conditions. We also introduce a suite of eight tasks that combine these three properties, and show that R2D3 can solve several of the tasks where other state of the art methods (both with and without demonstrations) fail to see even a single successful trajectory after tens of billions of steps of exploration."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.01387","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/1909.01387/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":"2026-07-05T00:02:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CnKwR+mfQKz1AiG6840psydd7a1PPOfaBlYEkI7ca+YdjstXbKg+y6m2otkhrZG6bzC0OMWUal+ngDttcIUkAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:57:18.720919Z"},"content_sha256":"a88a2c02674d747b31b5559951ab492842a1e21fc51cd06daedc55fc198ff623","schema_version":"1.0","event_id":"sha256:a88a2c02674d747b31b5559951ab492842a1e21fc51cd06daedc55fc198ff623"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IATTN4REXT4GBU4BYFHGNOGDVO/bundle.json","state_url":"https://pith.science/pith/IATTN4REXT4GBU4BYFHGNOGDVO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IATTN4REXT4GBU4BYFHGNOGDVO/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":"2026-08-08T12:57:18Z","links":{"resolver":"https://pith.science/pith/IATTN4REXT4GBU4BYFHGNOGDVO","bundle":"https://pith.science/pith/IATTN4REXT4GBU4BYFHGNOGDVO/bundle.json","state":"https://pith.science/pith/IATTN4REXT4GBU4BYFHGNOGDVO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IATTN4REXT4GBU4BYFHGNOGDVO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:IATTN4REXT4GBU4BYFHGNOGDVO","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":"9cb0a79cef24d4680b0d12d55878f7307e01c482615e4357fe437c8723b467c4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-03T18:20:48Z","title_canon_sha256":"b388e9874d112092568ec6f2a7fc2dbf7d9bb10506ea9b0f8cee2f441dc11a20"},"schema_version":"1.0","source":{"id":"1909.01387","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.01387","created_at":"2026-07-05T00:02:15Z"},{"alias_kind":"arxiv_version","alias_value":"1909.01387v1","created_at":"2026-07-05T00:02:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.01387","created_at":"2026-07-05T00:02:15Z"},{"alias_kind":"pith_short_12","alias_value":"IATTN4REXT4G","created_at":"2026-07-05T00:02:15Z"},{"alias_kind":"pith_short_16","alias_value":"IATTN4REXT4GBU4B","created_at":"2026-07-05T00:02:15Z"},{"alias_kind":"pith_short_8","alias_value":"IATTN4RE","created_at":"2026-07-05T00:02:15Z"}],"graph_snapshots":[{"event_id":"sha256:a88a2c02674d747b31b5559951ab492842a1e21fc51cd06daedc55fc198ff623","target":"graph","created_at":"2026-07-05T00:02:15Z","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/1909.01387/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces R2D3, an agent that makes efficient use of demonstrations to solve hard exploration problems in partially observable environments with highly variable initial conditions. We also introduce a suite of eight tasks that combine these three properties, and show that R2D3 can solve several of the tasks where other state of the art methods (both with and without demonstrations) fail to see even a single successful trajectory after tens of billions of steps of exploration.","authors_text":"Bobak Shahriari, Caglar Gulcehre, Duncan Williams, Gabriel Barth-Maron, Hubert Soyer, Matt Hoffman, Misha Denil, Nando de Freitas, Neil Rabinowitz, Richard Tanburn, Steven Kapturowski, Tom Le Paine, Worlds Team, Ziyu Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-03T18:20:48Z","title":"Making Efficient Use of Demonstrations to Solve Hard Exploration Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.01387","kind":"arxiv","version":1},"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:fb57fd3e351447100471a7a04327957a025a821cb5f3ec87c1c66ca5b9cbc0af","target":"record","created_at":"2026-07-05T00:02:15Z","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":"9cb0a79cef24d4680b0d12d55878f7307e01c482615e4357fe437c8723b467c4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-03T18:20:48Z","title_canon_sha256":"b388e9874d112092568ec6f2a7fc2dbf7d9bb10506ea9b0f8cee2f441dc11a20"},"schema_version":"1.0","source":{"id":"1909.01387","kind":"arxiv","version":1}},"canonical_sha256":"402736f224bcf860d381c14e66b8c3abb34e929f3c42589131cd6984365523c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"402736f224bcf860d381c14e66b8c3abb34e929f3c42589131cd6984365523c3","first_computed_at":"2026-07-05T00:02:15.680592Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:02:15.680592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QOtkP9WxZgmC92vx1gd1+pM4G1DXrXfX8kkZTRpmw8UpuKxU+oLLbrWOBa4U5vFuwrsEMokudxE5UxxriqC/Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:02:15.681068Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.01387","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb57fd3e351447100471a7a04327957a025a821cb5f3ec87c1c66ca5b9cbc0af","sha256:a88a2c02674d747b31b5559951ab492842a1e21fc51cd06daedc55fc198ff623"],"state_sha256":"2bce01543a4cda36cdb86b107fa971b13b66fee81e383b05df3a859c80dae473"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tKZrhvfTEp2DO/5gVZqCj4RSpVPU6aDELAUL9o01Ranh+fjJPz5XYf7vGgKFvZ5Nv/wAgkRBLiOAJ8A7SxBYDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:57:18.724850Z","bundle_sha256":"9e47f0e1c2c73cbf2d1ae4347e8165893996b697844196c0f1c0d452871fbc92"}}