{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:O2L23Z2FNSFPFPM6Y57Z3N4H6C","short_pith_number":"pith:O2L23Z2F","canonical_record":{"source":{"id":"1901.09732","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-28T15:25:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d5bbb2744a40fee10d36e917bf5f6991ef5edc1ea881c393c6d1283f3dd8cd3b","abstract_canon_sha256":"01a9df855e25fba004e54cbf2b14a4c1f23decc67b4d82e7a5083f4166459413"},"schema_version":"1.0"},"canonical_sha256":"7697ade7456c8af2bd9ec77f9db787f0a0a55f61f8f07390cd9e4bc9b6ddd1f0","source":{"kind":"arxiv","id":"1901.09732","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.09732","created_at":"2026-05-17T23:55:16Z"},{"alias_kind":"arxiv_version","alias_value":"1901.09732v2","created_at":"2026-05-17T23:55:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.09732","created_at":"2026-05-17T23:55:16Z"},{"alias_kind":"pith_short_12","alias_value":"O2L23Z2FNSFP","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"O2L23Z2FNSFPFPM6","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"O2L23Z2F","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:O2L23Z2FNSFPFPM6Y57Z3N4H6C","target":"record","payload":{"canonical_record":{"source":{"id":"1901.09732","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-28T15:25:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d5bbb2744a40fee10d36e917bf5f6991ef5edc1ea881c393c6d1283f3dd8cd3b","abstract_canon_sha256":"01a9df855e25fba004e54cbf2b14a4c1f23decc67b4d82e7a5083f4166459413"},"schema_version":"1.0"},"canonical_sha256":"7697ade7456c8af2bd9ec77f9db787f0a0a55f61f8f07390cd9e4bc9b6ddd1f0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:16.636381Z","signature_b64":"ZiJs0iIU7P2112x5WtcMjEF1UNxpb5WeCApbCOvYERklBnBuZmAxILlh4JA33qX+Pjyny2hYJ44QkHFpX1Z/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7697ade7456c8af2bd9ec77f9db787f0a0a55f61f8f07390cd9e4bc9b6ddd1f0","last_reissued_at":"2026-05-17T23:55:16.635915Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:16.635915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.09732","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":"2026-05-17T23:55:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LiRHgMVRT4E+NLVhg9p7YFvbKpOmqh4RUxaisirg2LmaELT5h1kR3wi5Fw+c3wQr5lHL8WTN8dHqQqaBIweFCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T15:19:21.553182Z"},"content_sha256":"bb8f0a9a84c48cb93d1a7f8a03bac8540a1afb4ebb508ecdaab1d09265d4a677","schema_version":"1.0","event_id":"sha256:bb8f0a9a84c48cb93d1a7f8a03bac8540a1afb4ebb508ecdaab1d09265d4a677"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:O2L23Z2FNSFPFPM6Y57Z3N4H6C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Making Deep Q-learning methods robust to time discretization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Corentin Tallec, L\\'eonard Blier, Yann Ollivier","submitted_at":"2019-01-28T15:25:10Z","abstract_excerpt":"Despite remarkable successes, Deep Reinforcement Learning (DRL) is not robust to hyperparameterization, implementation details, or small environment changes (Henderson et al. 2017, Zhang et al. 2018). Overcoming such sensitivity is key to making DRL applicable to real world problems. In this paper, we identify sensitivity to time discretization in near continuous-time environments as a critical factor; this covers, e.g., changing the number of frames per second, or the action frequency of the controller. Empirically, we find that Q-learning-based approaches such as Deep Q- learning (Mnih et al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.09732","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":""},"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":"2026-05-17T23:55:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ekecf9sunyMrr7B7JaGJFeR4twvZw1BmPqNydNbPu4+TwMDiev08WD0+nkRcSSVSV85hFkcuQaf6Fa/oUZ81CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T15:19:21.553758Z"},"content_sha256":"9f9d5a89c03f29e8ecbe18c50f325cd767a8e701e428317e233cf01264f05f88","schema_version":"1.0","event_id":"sha256:9f9d5a89c03f29e8ecbe18c50f325cd767a8e701e428317e233cf01264f05f88"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O2L23Z2FNSFPFPM6Y57Z3N4H6C/bundle.json","state_url":"https://pith.science/pith/O2L23Z2FNSFPFPM6Y57Z3N4H6C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O2L23Z2FNSFPFPM6Y57Z3N4H6C/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":"2026-05-31T15:19:21Z","links":{"resolver":"https://pith.science/pith/O2L23Z2FNSFPFPM6Y57Z3N4H6C","bundle":"https://pith.science/pith/O2L23Z2FNSFPFPM6Y57Z3N4H6C/bundle.json","state":"https://pith.science/pith/O2L23Z2FNSFPFPM6Y57Z3N4H6C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O2L23Z2FNSFPFPM6Y57Z3N4H6C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:O2L23Z2FNSFPFPM6Y57Z3N4H6C","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":"01a9df855e25fba004e54cbf2b14a4c1f23decc67b4d82e7a5083f4166459413","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-28T15:25:10Z","title_canon_sha256":"d5bbb2744a40fee10d36e917bf5f6991ef5edc1ea881c393c6d1283f3dd8cd3b"},"schema_version":"1.0","source":{"id":"1901.09732","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.09732","created_at":"2026-05-17T23:55:16Z"},{"alias_kind":"arxiv_version","alias_value":"1901.09732v2","created_at":"2026-05-17T23:55:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.09732","created_at":"2026-05-17T23:55:16Z"},{"alias_kind":"pith_short_12","alias_value":"O2L23Z2FNSFP","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"O2L23Z2FNSFPFPM6","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"O2L23Z2F","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:9f9d5a89c03f29e8ecbe18c50f325cd767a8e701e428317e233cf01264f05f88","target":"graph","created_at":"2026-05-17T23:55:16Z","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":"Despite remarkable successes, Deep Reinforcement Learning (DRL) is not robust to hyperparameterization, implementation details, or small environment changes (Henderson et al. 2017, Zhang et al. 2018). Overcoming such sensitivity is key to making DRL applicable to real world problems. In this paper, we identify sensitivity to time discretization in near continuous-time environments as a critical factor; this covers, e.g., changing the number of frames per second, or the action frequency of the controller. Empirically, we find that Q-learning-based approaches such as Deep Q- learning (Mnih et al","authors_text":"Corentin Tallec, L\\'eonard Blier, Yann Ollivier","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-28T15:25:10Z","title":"Making Deep Q-learning methods robust to time discretization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.09732","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:bb8f0a9a84c48cb93d1a7f8a03bac8540a1afb4ebb508ecdaab1d09265d4a677","target":"record","created_at":"2026-05-17T23:55:16Z","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":"01a9df855e25fba004e54cbf2b14a4c1f23decc67b4d82e7a5083f4166459413","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-28T15:25:10Z","title_canon_sha256":"d5bbb2744a40fee10d36e917bf5f6991ef5edc1ea881c393c6d1283f3dd8cd3b"},"schema_version":"1.0","source":{"id":"1901.09732","kind":"arxiv","version":2}},"canonical_sha256":"7697ade7456c8af2bd9ec77f9db787f0a0a55f61f8f07390cd9e4bc9b6ddd1f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7697ade7456c8af2bd9ec77f9db787f0a0a55f61f8f07390cd9e4bc9b6ddd1f0","first_computed_at":"2026-05-17T23:55:16.635915Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:16.635915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZiJs0iIU7P2112x5WtcMjEF1UNxpb5WeCApbCOvYERklBnBuZmAxILlh4JA33qX+Pjyny2hYJ44QkHFpX1Z/Ag==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:16.636381Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.09732","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb8f0a9a84c48cb93d1a7f8a03bac8540a1afb4ebb508ecdaab1d09265d4a677","sha256:9f9d5a89c03f29e8ecbe18c50f325cd767a8e701e428317e233cf01264f05f88"],"state_sha256":"5bfa5b581bc2879de7dc62e800b63d199e72b2b0ab2b97e9bfc4d8d5a5f42ef0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ETibep+eyKHedhDcvIuSh4Nq8Bt+OV7eIntAyi6VYxHcguTbY2ODXJS6Ia448p2V7wGKfloPWbLEyBVQ09RpCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T15:19:21.557883Z","bundle_sha256":"6bbf4eb92d0f6b528ae59d07f4e3abb3ae0819c81a8fdd30ffe1903a9d89f50f"}}