{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:SRSEFYLUTMDMYYGYK6TMOQLQ3Z","short_pith_number":"pith:SRSEFYLU","canonical_record":{"source":{"id":"2106.15419","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-29T13:38:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"beb612334d54cf5f8dcb109e75e7ffda4781296a2060fd43faced24eacef6bc3","abstract_canon_sha256":"0483f4022e11341fb5a47dbf4f7fc05528bf8bb10e6e5cbf217c91149a2a6cc5"},"schema_version":"1.0"},"canonical_sha256":"946442e1749b06cc60d857a6c74170de505064b7ac2d8bff0ac308f606a887e0","source":{"kind":"arxiv","id":"2106.15419","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.15419","created_at":"2026-07-05T04:19:32Z"},{"alias_kind":"arxiv_version","alias_value":"2106.15419v3","created_at":"2026-07-05T04:19:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.15419","created_at":"2026-07-05T04:19:32Z"},{"alias_kind":"pith_short_12","alias_value":"SRSEFYLUTMDM","created_at":"2026-07-05T04:19:32Z"},{"alias_kind":"pith_short_16","alias_value":"SRSEFYLUTMDMYYGY","created_at":"2026-07-05T04:19:32Z"},{"alias_kind":"pith_short_8","alias_value":"SRSEFYLU","created_at":"2026-07-05T04:19:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:SRSEFYLUTMDMYYGYK6TMOQLQ3Z","target":"record","payload":{"canonical_record":{"source":{"id":"2106.15419","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-29T13:38:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"beb612334d54cf5f8dcb109e75e7ffda4781296a2060fd43faced24eacef6bc3","abstract_canon_sha256":"0483f4022e11341fb5a47dbf4f7fc05528bf8bb10e6e5cbf217c91149a2a6cc5"},"schema_version":"1.0"},"canonical_sha256":"946442e1749b06cc60d857a6c74170de505064b7ac2d8bff0ac308f606a887e0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:19:32.992238Z","signature_b64":"YZxJ0R9oZ/gUXR0ix1h6gUeyp1N5IEQxHhyc47tyqVqea1fmtgsTu5uZSJnYn2VUZusvufNxx6kmGOwcXrtLBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"946442e1749b06cc60d857a6c74170de505064b7ac2d8bff0ac308f606a887e0","last_reissued_at":"2026-07-05T04:19:32.991773Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:19:32.991773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.15419","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":"2026-07-05T04:19:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oq2psWLQ6ds5XxRZq+tc1V7OxfZ0TKfq9Ebyco9xJlQHnVzIzModwcNcHkHuML/TlaIgSl6LxHYdjlNKkQDDBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:05:44.965930Z"},"content_sha256":"6627bdbc30a8856ff5eccfc6ccca0335dcba70838858b156af44420f6c5b5511","schema_version":"1.0","event_id":"sha256:6627bdbc30a8856ff5eccfc6ccca0335dcba70838858b156af44420f6c5b5511"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:SRSEFYLUTMDMYYGYK6TMOQLQ3Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Convergent and Efficient Deep Q Network Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Masahito Ueda, Zhikang T. Wang","submitted_at":"2021-06-29T13:38:59Z","abstract_excerpt":"Despite the empirical success of the deep Q network (DQN) reinforcement learning algorithm and its variants, DQN is still not well understood and it does not guarantee convergence. In this work, we show that DQN can indeed diverge and cease to operate in realistic settings. Although there exist gradient-based convergent methods, we show that they actually have inherent problems in learning dynamics which cause them to fail even in simple tasks. To overcome these problems, we propose a convergent DQN algorithm (C-DQN) that is guaranteed to converge and can work with large discount factors (0.99"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.15419","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/2106.15419/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":"2026-07-05T04:19:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WRqZv71COowwPAg3fH72K1+W6jpogacZBtgrbuo3fGDk3Om2Z4bOHdE2pc0JeF3kNp9jnecUuqnoN06uPsaMDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:05:44.966792Z"},"content_sha256":"5b3db793eb16e30f681119aba0018b6afb2b07a918eecaea2e1c5f4f6073e1cf","schema_version":"1.0","event_id":"sha256:5b3db793eb16e30f681119aba0018b6afb2b07a918eecaea2e1c5f4f6073e1cf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SRSEFYLUTMDMYYGYK6TMOQLQ3Z/bundle.json","state_url":"https://pith.science/pith/SRSEFYLUTMDMYYGYK6TMOQLQ3Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SRSEFYLUTMDMYYGYK6TMOQLQ3Z/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":"2026-08-11T01:05:44Z","links":{"resolver":"https://pith.science/pith/SRSEFYLUTMDMYYGYK6TMOQLQ3Z","bundle":"https://pith.science/pith/SRSEFYLUTMDMYYGYK6TMOQLQ3Z/bundle.json","state":"https://pith.science/pith/SRSEFYLUTMDMYYGYK6TMOQLQ3Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SRSEFYLUTMDMYYGYK6TMOQLQ3Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:SRSEFYLUTMDMYYGYK6TMOQLQ3Z","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":"0483f4022e11341fb5a47dbf4f7fc05528bf8bb10e6e5cbf217c91149a2a6cc5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-29T13:38:59Z","title_canon_sha256":"beb612334d54cf5f8dcb109e75e7ffda4781296a2060fd43faced24eacef6bc3"},"schema_version":"1.0","source":{"id":"2106.15419","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.15419","created_at":"2026-07-05T04:19:32Z"},{"alias_kind":"arxiv_version","alias_value":"2106.15419v3","created_at":"2026-07-05T04:19:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.15419","created_at":"2026-07-05T04:19:32Z"},{"alias_kind":"pith_short_12","alias_value":"SRSEFYLUTMDM","created_at":"2026-07-05T04:19:32Z"},{"alias_kind":"pith_short_16","alias_value":"SRSEFYLUTMDMYYGY","created_at":"2026-07-05T04:19:32Z"},{"alias_kind":"pith_short_8","alias_value":"SRSEFYLU","created_at":"2026-07-05T04:19:32Z"}],"graph_snapshots":[{"event_id":"sha256:5b3db793eb16e30f681119aba0018b6afb2b07a918eecaea2e1c5f4f6073e1cf","target":"graph","created_at":"2026-07-05T04:19:32Z","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/2106.15419/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the empirical success of the deep Q network (DQN) reinforcement learning algorithm and its variants, DQN is still not well understood and it does not guarantee convergence. In this work, we show that DQN can indeed diverge and cease to operate in realistic settings. Although there exist gradient-based convergent methods, we show that they actually have inherent problems in learning dynamics which cause them to fail even in simple tasks. To overcome these problems, we propose a convergent DQN algorithm (C-DQN) that is guaranteed to converge and can work with large discount factors (0.99","authors_text":"Masahito Ueda, Zhikang T. Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-29T13:38:59Z","title":"Convergent and Efficient Deep Q Network Algorithm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.15419","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":"sha256:6627bdbc30a8856ff5eccfc6ccca0335dcba70838858b156af44420f6c5b5511","target":"record","created_at":"2026-07-05T04:19:32Z","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":"0483f4022e11341fb5a47dbf4f7fc05528bf8bb10e6e5cbf217c91149a2a6cc5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-29T13:38:59Z","title_canon_sha256":"beb612334d54cf5f8dcb109e75e7ffda4781296a2060fd43faced24eacef6bc3"},"schema_version":"1.0","source":{"id":"2106.15419","kind":"arxiv","version":3}},"canonical_sha256":"946442e1749b06cc60d857a6c74170de505064b7ac2d8bff0ac308f606a887e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"946442e1749b06cc60d857a6c74170de505064b7ac2d8bff0ac308f606a887e0","first_computed_at":"2026-07-05T04:19:32.991773Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:19:32.991773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YZxJ0R9oZ/gUXR0ix1h6gUeyp1N5IEQxHhyc47tyqVqea1fmtgsTu5uZSJnYn2VUZusvufNxx6kmGOwcXrtLBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:19:32.992238Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.15419","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6627bdbc30a8856ff5eccfc6ccca0335dcba70838858b156af44420f6c5b5511","sha256:5b3db793eb16e30f681119aba0018b6afb2b07a918eecaea2e1c5f4f6073e1cf"],"state_sha256":"ea8f075b727f6e509aa0c2c6deefffe458a1130751db6f556b3889eb4087af52"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"baySgM7hTGapF9UnO358hJetdgmYKrdeMbHG1S4iBwKf4nT/L5li2IF3in6FBrrd+5jZeB18g7lCV7+hrTeVDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T01:05:44.988239Z","bundle_sha256":"6318417bf77392b1a691f5b275c6b66045d28a6aeb5b3c78fc697c2d2c5e423d"}}