{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:G4M6IW43WIR3CLEJJEQUMIWIPH","short_pith_number":"pith:G4M6IW43","canonical_record":{"source":{"id":"1806.08894","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-23T02:18:26Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"4e971f4c499247331bdf6f72ff04fc39a617c7cc6fe5b96a29027c6d365dfe3b","abstract_canon_sha256":"ea5dbeee2a9ac92ea6afd7a1039fdab76c8ab1b1654c6fddbf3c813460482252"},"schema_version":"1.0"},"canonical_sha256":"3719e45b9bb223b12c8949214622c879e24d92b0111506f03c616578028e1ee3","source":{"kind":"arxiv","id":"1806.08894","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.08894","created_at":"2026-05-18T00:12:30Z"},{"alias_kind":"arxiv_version","alias_value":"1806.08894v1","created_at":"2026-05-18T00:12:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.08894","created_at":"2026-05-18T00:12:30Z"},{"alias_kind":"pith_short_12","alias_value":"G4M6IW43WIR3","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"G4M6IW43WIR3CLEJ","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"G4M6IW43","created_at":"2026-05-18T12:32:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:G4M6IW43WIR3CLEJJEQUMIWIPH","target":"record","payload":{"canonical_record":{"source":{"id":"1806.08894","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-23T02:18:26Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"4e971f4c499247331bdf6f72ff04fc39a617c7cc6fe5b96a29027c6d365dfe3b","abstract_canon_sha256":"ea5dbeee2a9ac92ea6afd7a1039fdab76c8ab1b1654c6fddbf3c813460482252"},"schema_version":"1.0"},"canonical_sha256":"3719e45b9bb223b12c8949214622c879e24d92b0111506f03c616578028e1ee3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:30.987381Z","signature_b64":"5MZwHw60HMEe1cnAJcfQELu7tUWyiXFeeD8l54SCrVeIbW/Q55mmYxK1UFHSNvacOgbamkkDqKbnzwkvU8PSAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3719e45b9bb223b12c8949214622c879e24d92b0111506f03c616578028e1ee3","last_reissued_at":"2026-05-18T00:12:30.986779Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:30.986779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.08894","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":"2026-05-18T00:12:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dCehR7+QPRl6dn3ujJhAd5b7+f4ARnDjbT8ZHJD+Ak+RHhRLHDgj4TBvFo1+Zc0xCx8ZUc215a5lNEKQFFrlCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T04:24:17.507940Z"},"content_sha256":"02416eb4d8291c3da4de206bf8014f2309d1ea3fc43e15174f80d0d9239c19d0","schema_version":"1.0","event_id":"sha256:02416eb4d8291c3da4de206bf8014f2309d1ea3fc43e15174f80d0d9239c19d0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:G4M6IW43WIR3CLEJJEQUMIWIPH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning: An Overview","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Enda Howley, Michael Schukat, Seyed Sajad Mousavi","submitted_at":"2018-06-23T02:18:26Z","abstract_excerpt":"In recent years, a specific machine learning method called deep learning has gained huge attraction, as it has obtained astonishing results in broad applications such as pattern recognition, speech recognition, computer vision, and natural language processing. Recent research has also been shown that deep learning techniques can be combined with reinforcement learning methods to learn useful representations for the problems with high dimensional raw data input. This chapter reviews the recent advances in deep reinforcement learning with a focus on the most used deep architectures such as autoe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.08894","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":""},"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":"2026-05-18T00:12:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tbeIqxKOP546/3mDAep7tsjrjbjry6hkGu/qaV1qZDNcWQ2Sd5YYEjZYqZLiJzS0yD7I2jSVFKY9l7q3PFsxBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T04:24:17.508597Z"},"content_sha256":"71b7299119bfc027eb41bdccdcb02304b5c3b4a96eaa7b02386928f6cef0596f","schema_version":"1.0","event_id":"sha256:71b7299119bfc027eb41bdccdcb02304b5c3b4a96eaa7b02386928f6cef0596f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G4M6IW43WIR3CLEJJEQUMIWIPH/bundle.json","state_url":"https://pith.science/pith/G4M6IW43WIR3CLEJJEQUMIWIPH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G4M6IW43WIR3CLEJJEQUMIWIPH/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":"2026-08-24T04:24:17Z","links":{"resolver":"https://pith.science/pith/G4M6IW43WIR3CLEJJEQUMIWIPH","bundle":"https://pith.science/pith/G4M6IW43WIR3CLEJJEQUMIWIPH/bundle.json","state":"https://pith.science/pith/G4M6IW43WIR3CLEJJEQUMIWIPH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G4M6IW43WIR3CLEJJEQUMIWIPH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:G4M6IW43WIR3CLEJJEQUMIWIPH","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":"ea5dbeee2a9ac92ea6afd7a1039fdab76c8ab1b1654c6fddbf3c813460482252","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-23T02:18:26Z","title_canon_sha256":"4e971f4c499247331bdf6f72ff04fc39a617c7cc6fe5b96a29027c6d365dfe3b"},"schema_version":"1.0","source":{"id":"1806.08894","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.08894","created_at":"2026-05-18T00:12:30Z"},{"alias_kind":"arxiv_version","alias_value":"1806.08894v1","created_at":"2026-05-18T00:12:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.08894","created_at":"2026-05-18T00:12:30Z"},{"alias_kind":"pith_short_12","alias_value":"G4M6IW43WIR3","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"G4M6IW43WIR3CLEJ","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"G4M6IW43","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:71b7299119bfc027eb41bdccdcb02304b5c3b4a96eaa7b02386928f6cef0596f","target":"graph","created_at":"2026-05-18T00:12:30Z","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":"In recent years, a specific machine learning method called deep learning has gained huge attraction, as it has obtained astonishing results in broad applications such as pattern recognition, speech recognition, computer vision, and natural language processing. Recent research has also been shown that deep learning techniques can be combined with reinforcement learning methods to learn useful representations for the problems with high dimensional raw data input. This chapter reviews the recent advances in deep reinforcement learning with a focus on the most used deep architectures such as autoe","authors_text":"Enda Howley, Michael Schukat, Seyed Sajad Mousavi","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-23T02:18:26Z","title":"Deep Reinforcement Learning: An Overview"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.08894","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":"sha256:02416eb4d8291c3da4de206bf8014f2309d1ea3fc43e15174f80d0d9239c19d0","target":"record","created_at":"2026-05-18T00:12:30Z","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":"ea5dbeee2a9ac92ea6afd7a1039fdab76c8ab1b1654c6fddbf3c813460482252","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-23T02:18:26Z","title_canon_sha256":"4e971f4c499247331bdf6f72ff04fc39a617c7cc6fe5b96a29027c6d365dfe3b"},"schema_version":"1.0","source":{"id":"1806.08894","kind":"arxiv","version":1}},"canonical_sha256":"3719e45b9bb223b12c8949214622c879e24d92b0111506f03c616578028e1ee3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3719e45b9bb223b12c8949214622c879e24d92b0111506f03c616578028e1ee3","first_computed_at":"2026-05-18T00:12:30.986779Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:12:30.986779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5MZwHw60HMEe1cnAJcfQELu7tUWyiXFeeD8l54SCrVeIbW/Q55mmYxK1UFHSNvacOgbamkkDqKbnzwkvU8PSAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:12:30.987381Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.08894","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02416eb4d8291c3da4de206bf8014f2309d1ea3fc43e15174f80d0d9239c19d0","sha256:71b7299119bfc027eb41bdccdcb02304b5c3b4a96eaa7b02386928f6cef0596f"],"state_sha256":"a29cf31442fdd03407fec7ca5cb1e50333092233b3efe108d6803bc1c18755d3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ud1u0LW9EdJFd1tgd1IofUrzPMd6LIPKLgohsMJZw9EEM6oOhHUX5fnn9Xm1td2dXWvsKUVtgSMv/+dZiLHnCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-24T04:24:17.513754Z","bundle_sha256":"4c2491308095923ec2c6dda02299be2171bb6ab320c53f05b2bd91e49957f1b8"}}