{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:4TF2PFST4AYJSP7V6CL26BVBGV","short_pith_number":"pith:4TF2PFST","canonical_record":{"source":{"id":"1704.03732","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-04-12T12:44:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"15c6de0049e5300bd9e46aa894cc50b67c4421d0e641e7d747b89b398a32b2c5","abstract_canon_sha256":"be25f9b75ff99dea0eb1500a831034d786bd9e8897e0b1903705bf8cdeda07b5"},"schema_version":"1.0"},"canonical_sha256":"e4cba79653e030993ff5f097af06a1355f80f24e999550f80a45a405c9521d23","source":{"kind":"arxiv","id":"1704.03732","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.03732","created_at":"2026-05-18T00:29:46Z"},{"alias_kind":"arxiv_version","alias_value":"1704.03732v4","created_at":"2026-05-18T00:29:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.03732","created_at":"2026-05-18T00:29:46Z"},{"alias_kind":"pith_short_12","alias_value":"4TF2PFST4AYJ","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"4TF2PFST4AYJSP7V","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"4TF2PFST","created_at":"2026-05-18T12:31:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:4TF2PFST4AYJSP7V6CL26BVBGV","target":"record","payload":{"canonical_record":{"source":{"id":"1704.03732","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-04-12T12:44:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"15c6de0049e5300bd9e46aa894cc50b67c4421d0e641e7d747b89b398a32b2c5","abstract_canon_sha256":"be25f9b75ff99dea0eb1500a831034d786bd9e8897e0b1903705bf8cdeda07b5"},"schema_version":"1.0"},"canonical_sha256":"e4cba79653e030993ff5f097af06a1355f80f24e999550f80a45a405c9521d23","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:46.197389Z","signature_b64":"SSfsDGOhD1GQPV4Yx+ClJRP4GEHljiO/pJtvj2JBM8mQ1YrjhUr73+iPbjH81Bo2tLYajmZ7KwgWRwFDDlq3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4cba79653e030993ff5f097af06a1355f80f24e999550f80a45a405c9521d23","last_reissued_at":"2026-05-18T00:29:46.196823Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:46.196823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1704.03732","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:29:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7UIVsqDbZdDmEuvEzQ2kSGhjEuzOuHEo5MKXGvBKaV343HMVNKk5bgUkDhTz56L/SK0D2BYJWSPwarOWvHEsDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T04:57:20.587028Z"},"content_sha256":"c921d6bfe7a2c7db8e10a2e7d6129f1f09c8a47143aa0cd6fb9b7424125fe887","schema_version":"1.0","event_id":"sha256:c921d6bfe7a2c7db8e10a2e7d6129f1f09c8a47143aa0cd6fb9b7424125fe887"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:4TF2PFST4AYJSP7V6CL26BVBGV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Q-learning from Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Andrew Sendonaris, Audrunas Gruslys, Bilal Piot, Dan Horgan, Gabriel Dulac-Arnold, Ian Osband, Joel Z. Leibo, John Agapiou, John Quan, Marc Lanctot, Matej Vecerik, Olivier Pietquin, Todd Hester, Tom Schaul","submitted_at":"2017-04-12T12:44:37Z","abstract_excerpt":"Deep reinforcement learning (RL) has achieved several high profile successes in difficult decision-making problems. However, these algorithms typically require a huge amount of data before they reach reasonable performance. In fact, their performance during learning can be extremely poor. This may be acceptable for a simulator, but it severely limits the applicability of deep RL to many real-world tasks, where the agent must learn in the real environment. In this paper we study a setting where the agent may access data from previous control of the system. We present an algorithm, Deep Q-learni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.03732","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":""},"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":"2026-05-18T00:29:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+4d+gebbHBudNcCuvit77Kap9l4vUN83fq5JJszCuRcFi+OZV5tQ36/JvDfoSf/CK5R8VihUj3C4NN2gZNTvDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T04:57:20.587396Z"},"content_sha256":"60533937fa16d8e58674a612dc68afa784758f1bb28bf3e33d16773cc95294a9","schema_version":"1.0","event_id":"sha256:60533937fa16d8e58674a612dc68afa784758f1bb28bf3e33d16773cc95294a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4TF2PFST4AYJSP7V6CL26BVBGV/bundle.json","state_url":"https://pith.science/pith/4TF2PFST4AYJSP7V6CL26BVBGV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4TF2PFST4AYJSP7V6CL26BVBGV/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":"2026-05-30T04:57:20Z","links":{"resolver":"https://pith.science/pith/4TF2PFST4AYJSP7V6CL26BVBGV","bundle":"https://pith.science/pith/4TF2PFST4AYJSP7V6CL26BVBGV/bundle.json","state":"https://pith.science/pith/4TF2PFST4AYJSP7V6CL26BVBGV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4TF2PFST4AYJSP7V6CL26BVBGV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:4TF2PFST4AYJSP7V6CL26BVBGV","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":"be25f9b75ff99dea0eb1500a831034d786bd9e8897e0b1903705bf8cdeda07b5","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-04-12T12:44:37Z","title_canon_sha256":"15c6de0049e5300bd9e46aa894cc50b67c4421d0e641e7d747b89b398a32b2c5"},"schema_version":"1.0","source":{"id":"1704.03732","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.03732","created_at":"2026-05-18T00:29:46Z"},{"alias_kind":"arxiv_version","alias_value":"1704.03732v4","created_at":"2026-05-18T00:29:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.03732","created_at":"2026-05-18T00:29:46Z"},{"alias_kind":"pith_short_12","alias_value":"4TF2PFST4AYJ","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"4TF2PFST4AYJSP7V","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"4TF2PFST","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:60533937fa16d8e58674a612dc68afa784758f1bb28bf3e33d16773cc95294a9","target":"graph","created_at":"2026-05-18T00:29:46Z","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"},"paper":{"abstract_excerpt":"Deep reinforcement learning (RL) has achieved several high profile successes in difficult decision-making problems. However, these algorithms typically require a huge amount of data before they reach reasonable performance. In fact, their performance during learning can be extremely poor. This may be acceptable for a simulator, but it severely limits the applicability of deep RL to many real-world tasks, where the agent must learn in the real environment. In this paper we study a setting where the agent may access data from previous control of the system. We present an algorithm, Deep Q-learni","authors_text":"Andrew Sendonaris, Audrunas Gruslys, Bilal Piot, Dan Horgan, Gabriel Dulac-Arnold, Ian Osband, Joel Z. Leibo, John Agapiou, John Quan, Marc Lanctot, Matej Vecerik, Olivier Pietquin, Todd Hester, Tom Schaul","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-04-12T12:44:37Z","title":"Deep Q-learning from Demonstrations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.03732","kind":"arxiv","version":4},"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:c921d6bfe7a2c7db8e10a2e7d6129f1f09c8a47143aa0cd6fb9b7424125fe887","target":"record","created_at":"2026-05-18T00:29:46Z","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":"be25f9b75ff99dea0eb1500a831034d786bd9e8897e0b1903705bf8cdeda07b5","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-04-12T12:44:37Z","title_canon_sha256":"15c6de0049e5300bd9e46aa894cc50b67c4421d0e641e7d747b89b398a32b2c5"},"schema_version":"1.0","source":{"id":"1704.03732","kind":"arxiv","version":4}},"canonical_sha256":"e4cba79653e030993ff5f097af06a1355f80f24e999550f80a45a405c9521d23","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e4cba79653e030993ff5f097af06a1355f80f24e999550f80a45a405c9521d23","first_computed_at":"2026-05-18T00:29:46.196823Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:29:46.196823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SSfsDGOhD1GQPV4Yx+ClJRP4GEHljiO/pJtvj2JBM8mQ1YrjhUr73+iPbjH81Bo2tLYajmZ7KwgWRwFDDlq3AQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:29:46.197389Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.03732","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c921d6bfe7a2c7db8e10a2e7d6129f1f09c8a47143aa0cd6fb9b7424125fe887","sha256:60533937fa16d8e58674a612dc68afa784758f1bb28bf3e33d16773cc95294a9"],"state_sha256":"348d9b4d9d1cd14ff9e6088b04bc28773c67fd51e509c5aed93fbe4f21ca5f8c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lKZkEjB6vjr9z87Y3bBDm+lX0+uFDXVA32IC4Aeil1J8hvJuWTL7M38tpG2WWI/3wzsEPS3gFkkZhf+VvjxHAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T04:57:20.589347Z","bundle_sha256":"def47f2d25725d42a0ea1a0d214c8562b3df5e0cae5a3ab622b47b83d86b7236"}}