{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:PBK46MGZZJL5FK75S46P5IUV3C","short_pith_number":"pith:PBK46MGZ","canonical_record":{"source":{"id":"1912.10944","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2019-12-23T16:04:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"cf5d490ae0f12aba266f0b78578d4d7ffe0a7e39a1f24ebd9d92831982bad6f4","abstract_canon_sha256":"9acd92a4095c60e03f4b2446de4cccc5689cd0d21b5dc9781dbded4ab1d93839"},"schema_version":"1.0"},"canonical_sha256":"7855cf30d9ca57d2abfd973cfea295d89257adc198257f88da58d33ce0adaca7","source":{"kind":"arxiv","id":"1912.10944","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.10944","created_at":"2026-07-05T00:28:26Z"},{"alias_kind":"arxiv_version","alias_value":"1912.10944v2","created_at":"2026-07-05T00:28:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.10944","created_at":"2026-07-05T00:28:26Z"},{"alias_kind":"pith_short_12","alias_value":"PBK46MGZZJL5","created_at":"2026-07-05T00:28:26Z"},{"alias_kind":"pith_short_16","alias_value":"PBK46MGZZJL5FK75","created_at":"2026-07-05T00:28:26Z"},{"alias_kind":"pith_short_8","alias_value":"PBK46MGZ","created_at":"2026-07-05T00:28:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:PBK46MGZZJL5FK75S46P5IUV3C","target":"record","payload":{"canonical_record":{"source":{"id":"1912.10944","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2019-12-23T16:04:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"cf5d490ae0f12aba266f0b78578d4d7ffe0a7e39a1f24ebd9d92831982bad6f4","abstract_canon_sha256":"9acd92a4095c60e03f4b2446de4cccc5689cd0d21b5dc9781dbded4ab1d93839"},"schema_version":"1.0"},"canonical_sha256":"7855cf30d9ca57d2abfd973cfea295d89257adc198257f88da58d33ce0adaca7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:28:26.164146Z","signature_b64":"sAyFUosBcTdjDJdSZjKwSFQWIFRQT86NG2RhfJ9znUzTZrTHfZvdPma5KkeQRMThUsqAHCUaVHsGavsjDOUTDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7855cf30d9ca57d2abfd973cfea295d89257adc198257f88da58d33ce0adaca7","last_reissued_at":"2026-07-05T00:28:26.163750Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:28:26.163750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1912.10944","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:28:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4RWDBVj6XIN3khn2ZbSFUQ35eJidgxFduT4ajkxmLpSvsoZ5rUDkGkqz03QMuc0GcHtg6wOCZmZv5aiZaxrFAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T12:46:18.570888Z"},"content_sha256":"054ed0cd5a02dc6c9a3d0bc8b68588e320363f35fd8edab710c8dc00ef62a114","schema_version":"1.0","event_id":"sha256:054ed0cd5a02dc6c9a3d0bc8b68588e320363f35fd8edab710c8dc00ef62a114"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:PBK46MGZZJL5FK75S46P5IUV3C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey of Deep Reinforcement Learning in Video Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.MA","authors_text":"Dongbin Zhao, Kun Shao, Nannan Li, Yuanheng Zhu, Zhentao Tang","submitted_at":"2019-12-23T16:04:40Z","abstract_excerpt":"Deep reinforcement learning (DRL) has made great achievements since proposed. Generally, DRL agents receive high-dimensional inputs at each step, and make actions according to deep-neural-network-based policies. This learning mechanism updates the policy to maximize the return with an end-to-end method. In this paper, we survey the progress of DRL methods, including value-based, policy gradient, and model-based algorithms, and compare their main techniques and properties. Besides, DRL plays an important role in game artificial intelligence (AI). We also take a review of the achievements of DRL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.10944","kind":"arxiv","version":2},"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/1912.10944/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":"2026-07-05T00:28:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R7VCivXOexv0FeDI6MgPkNmX1g6wTkCi/nHP52yamDkPlPV/zlGMHbQ7Le9Kd7m6/BKkCyqQBuxAJ5dreh+FAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T12:46:18.571778Z"},"content_sha256":"ea7b88efcffc4512e0a305d0cd02397d743cdf3aa90017babe0ac05502a0c524","schema_version":"1.0","event_id":"sha256:ea7b88efcffc4512e0a305d0cd02397d743cdf3aa90017babe0ac05502a0c524"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PBK46MGZZJL5FK75S46P5IUV3C/bundle.json","state_url":"https://pith.science/pith/PBK46MGZZJL5FK75S46P5IUV3C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PBK46MGZZJL5FK75S46P5IUV3C/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":"2026-08-19T12:46:18Z","links":{"resolver":"https://pith.science/pith/PBK46MGZZJL5FK75S46P5IUV3C","bundle":"https://pith.science/pith/PBK46MGZZJL5FK75S46P5IUV3C/bundle.json","state":"https://pith.science/pith/PBK46MGZZJL5FK75S46P5IUV3C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PBK46MGZZJL5FK75S46P5IUV3C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:PBK46MGZZJL5FK75S46P5IUV3C","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":"9acd92a4095c60e03f4b2446de4cccc5689cd0d21b5dc9781dbded4ab1d93839","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2019-12-23T16:04:40Z","title_canon_sha256":"cf5d490ae0f12aba266f0b78578d4d7ffe0a7e39a1f24ebd9d92831982bad6f4"},"schema_version":"1.0","source":{"id":"1912.10944","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.10944","created_at":"2026-07-05T00:28:26Z"},{"alias_kind":"arxiv_version","alias_value":"1912.10944v2","created_at":"2026-07-05T00:28:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.10944","created_at":"2026-07-05T00:28:26Z"},{"alias_kind":"pith_short_12","alias_value":"PBK46MGZZJL5","created_at":"2026-07-05T00:28:26Z"},{"alias_kind":"pith_short_16","alias_value":"PBK46MGZZJL5FK75","created_at":"2026-07-05T00:28:26Z"},{"alias_kind":"pith_short_8","alias_value":"PBK46MGZ","created_at":"2026-07-05T00:28:26Z"}],"graph_snapshots":[{"event_id":"sha256:ea7b88efcffc4512e0a305d0cd02397d743cdf3aa90017babe0ac05502a0c524","target":"graph","created_at":"2026-07-05T00:28:26Z","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/1912.10944/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning (DRL) has made great achievements since proposed. Generally, DRL agents receive high-dimensional inputs at each step, and make actions according to deep-neural-network-based policies. This learning mechanism updates the policy to maximize the return with an end-to-end method. In this paper, we survey the progress of DRL methods, including value-based, policy gradient, and model-based algorithms, and compare their main techniques and properties. Besides, DRL plays an important role in game artificial intelligence (AI). We also take a review of the achievements of DRL","authors_text":"Dongbin Zhao, Kun Shao, Nannan Li, Yuanheng Zhu, Zhentao Tang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2019-12-23T16:04:40Z","title":"A Survey of Deep Reinforcement Learning in Video Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.10944","kind":"arxiv","version":2},"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":"sha256:054ed0cd5a02dc6c9a3d0bc8b68588e320363f35fd8edab710c8dc00ef62a114","target":"record","created_at":"2026-07-05T00:28:26Z","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":"9acd92a4095c60e03f4b2446de4cccc5689cd0d21b5dc9781dbded4ab1d93839","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2019-12-23T16:04:40Z","title_canon_sha256":"cf5d490ae0f12aba266f0b78578d4d7ffe0a7e39a1f24ebd9d92831982bad6f4"},"schema_version":"1.0","source":{"id":"1912.10944","kind":"arxiv","version":2}},"canonical_sha256":"7855cf30d9ca57d2abfd973cfea295d89257adc198257f88da58d33ce0adaca7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7855cf30d9ca57d2abfd973cfea295d89257adc198257f88da58d33ce0adaca7","first_computed_at":"2026-07-05T00:28:26.163750Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:28:26.163750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sAyFUosBcTdjDJdSZjKwSFQWIFRQT86NG2RhfJ9znUzTZrTHfZvdPma5KkeQRMThUsqAHCUaVHsGavsjDOUTDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:28:26.164146Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.10944","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:054ed0cd5a02dc6c9a3d0bc8b68588e320363f35fd8edab710c8dc00ef62a114","sha256:ea7b88efcffc4512e0a305d0cd02397d743cdf3aa90017babe0ac05502a0c524"],"state_sha256":"e3bdef1260b02dc570d216eede33695d6ef3baba8238949ff659cd83b253ceae"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ImAJrECRhGMF89k5b7BvLpbouyPwF8EORSpz2R+2FnpQALxhMFL2lkm8lPPr7AkB2AwFdsrnkOwFPqSC0P3lAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T12:46:18.579339Z","bundle_sha256":"e162517cff3bba5186398691dbd06c9ed8f1165ec5cd42e22a1ec31578bce0bc"}}