{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:NETGXAYQ5BGXZ2M7E73Y7GL4SR","short_pith_number":"pith:NETGXAYQ","canonical_record":{"source":{"id":"1805.07732","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-20T08:43:05Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"3e4274f579ad419fce1e9d8b727a437276ab6d32a377b5710587518bd95f2bb3","abstract_canon_sha256":"8a1d560dedf2e5fb2f66190da42ab83ffe0c9fa8b868328f9a4180ea66592063"},"schema_version":"1.0"},"canonical_sha256":"69266b8310e84d7ce99f27f78f997c947b0f23329701d07d1149f7a8b2b48b72","source":{"kind":"arxiv","id":"1805.07732","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.07732","created_at":"2026-05-17T23:49:33Z"},{"alias_kind":"arxiv_version","alias_value":"1805.07732v3","created_at":"2026-05-17T23:49:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07732","created_at":"2026-05-17T23:49:33Z"},{"alias_kind":"pith_short_12","alias_value":"NETGXAYQ5BGX","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"NETGXAYQ5BGXZ2M7","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"NETGXAYQ","created_at":"2026-05-18T12:32:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:NETGXAYQ5BGXZ2M7E73Y7GL4SR","target":"record","payload":{"canonical_record":{"source":{"id":"1805.07732","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-20T08:43:05Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"3e4274f579ad419fce1e9d8b727a437276ab6d32a377b5710587518bd95f2bb3","abstract_canon_sha256":"8a1d560dedf2e5fb2f66190da42ab83ffe0c9fa8b868328f9a4180ea66592063"},"schema_version":"1.0"},"canonical_sha256":"69266b8310e84d7ce99f27f78f997c947b0f23329701d07d1149f7a8b2b48b72","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:33.603535Z","signature_b64":"lgMXfaKjDX2vhmzBm6F6L38+o15PKih9BKkLMh7jzbpjeQSyFtLlVXl403yBmqzf9ocweg8fWPCNTKoR2YJqBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69266b8310e84d7ce99f27f78f997c947b0f23329701d07d1149f7a8b2b48b72","last_reissued_at":"2026-05-17T23:49:33.603034Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:33.603034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.07732","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":"2026-05-17T23:49:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KTL6BrNj6nGB/XPZcC5vbIjTHUW9DOwsJ7yi8CbGeZHOMwkrwZ9lXZnFVma7Y+11P8Dz6OjHpiJ8g+Ohh+wFAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T13:50:41.908293Z"},"content_sha256":"153824dd2e7c91b913e5e81ec073e768a7622b3db8be50810e4dcb1a8409a3e1","schema_version":"1.0","event_id":"sha256:153824dd2e7c91b913e5e81ec073e768a7622b3db8be50810e4dcb1a8409a3e1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:NETGXAYQ5BGXZ2M7E73Y7GL4SR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Nonlinear Distributional Gradient Temporal-Difference Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chao Qu, Huan Xu, Shie Mannor","submitted_at":"2018-05-20T08:43:05Z","abstract_excerpt":"We devise a distributional variant of gradient temporal-difference (TD) learning. Distributional reinforcement learning has been demonstrated to outperform the regular one in the recent study \\citep{bellemare2017distributional}. In the policy evaluation setting, we design two new algorithms called distributional GTD2 and distributional TDC using the Cram{\\'e}r distance on the distributional version of the Bellman error objective function, which inherits advantages of both the nonlinear gradient TD algorithms and the distributional RL approach. In the control setting, we propose the distributio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07732","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":""},"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":"2026-05-17T23:49:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OqVb5qKI3liMqmiHjYbktBegg7HGq9CoUAcfAiWs2p/V4ZBwSJML+QanXLaFe5/rQD4mIjdm9HWyhjB74ettCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T13:50:41.908661Z"},"content_sha256":"d39ee86afdb45e5e0ee12c61b1aa515ec86075193020c67329525407b384e932","schema_version":"1.0","event_id":"sha256:d39ee86afdb45e5e0ee12c61b1aa515ec86075193020c67329525407b384e932"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NETGXAYQ5BGXZ2M7E73Y7GL4SR/bundle.json","state_url":"https://pith.science/pith/NETGXAYQ5BGXZ2M7E73Y7GL4SR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NETGXAYQ5BGXZ2M7E73Y7GL4SR/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":"2026-05-31T13:50:41Z","links":{"resolver":"https://pith.science/pith/NETGXAYQ5BGXZ2M7E73Y7GL4SR","bundle":"https://pith.science/pith/NETGXAYQ5BGXZ2M7E73Y7GL4SR/bundle.json","state":"https://pith.science/pith/NETGXAYQ5BGXZ2M7E73Y7GL4SR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NETGXAYQ5BGXZ2M7E73Y7GL4SR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:NETGXAYQ5BGXZ2M7E73Y7GL4SR","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":"8a1d560dedf2e5fb2f66190da42ab83ffe0c9fa8b868328f9a4180ea66592063","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-20T08:43:05Z","title_canon_sha256":"3e4274f579ad419fce1e9d8b727a437276ab6d32a377b5710587518bd95f2bb3"},"schema_version":"1.0","source":{"id":"1805.07732","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.07732","created_at":"2026-05-17T23:49:33Z"},{"alias_kind":"arxiv_version","alias_value":"1805.07732v3","created_at":"2026-05-17T23:49:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07732","created_at":"2026-05-17T23:49:33Z"},{"alias_kind":"pith_short_12","alias_value":"NETGXAYQ5BGX","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"NETGXAYQ5BGXZ2M7","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"NETGXAYQ","created_at":"2026-05-18T12:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:d39ee86afdb45e5e0ee12c61b1aa515ec86075193020c67329525407b384e932","target":"graph","created_at":"2026-05-17T23:49:33Z","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":"We devise a distributional variant of gradient temporal-difference (TD) learning. Distributional reinforcement learning has been demonstrated to outperform the regular one in the recent study \\citep{bellemare2017distributional}. In the policy evaluation setting, we design two new algorithms called distributional GTD2 and distributional TDC using the Cram{\\'e}r distance on the distributional version of the Bellman error objective function, which inherits advantages of both the nonlinear gradient TD algorithms and the distributional RL approach. In the control setting, we propose the distributio","authors_text":"Chao Qu, Huan Xu, Shie Mannor","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-20T08:43:05Z","title":"Nonlinear Distributional Gradient Temporal-Difference Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07732","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":"sha256:153824dd2e7c91b913e5e81ec073e768a7622b3db8be50810e4dcb1a8409a3e1","target":"record","created_at":"2026-05-17T23:49:33Z","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":"8a1d560dedf2e5fb2f66190da42ab83ffe0c9fa8b868328f9a4180ea66592063","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-20T08:43:05Z","title_canon_sha256":"3e4274f579ad419fce1e9d8b727a437276ab6d32a377b5710587518bd95f2bb3"},"schema_version":"1.0","source":{"id":"1805.07732","kind":"arxiv","version":3}},"canonical_sha256":"69266b8310e84d7ce99f27f78f997c947b0f23329701d07d1149f7a8b2b48b72","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69266b8310e84d7ce99f27f78f997c947b0f23329701d07d1149f7a8b2b48b72","first_computed_at":"2026-05-17T23:49:33.603034Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:33.603034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lgMXfaKjDX2vhmzBm6F6L38+o15PKih9BKkLMh7jzbpjeQSyFtLlVXl403yBmqzf9ocweg8fWPCNTKoR2YJqBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:33.603535Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.07732","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:153824dd2e7c91b913e5e81ec073e768a7622b3db8be50810e4dcb1a8409a3e1","sha256:d39ee86afdb45e5e0ee12c61b1aa515ec86075193020c67329525407b384e932"],"state_sha256":"555e541b9df9a661ce1ce422b28189f1af3896fd197c109f1ed635d340d1ae3f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p+Au0B4Aj1jTX8d37JzrShHQGGqGjBTcX2TZ2XuyOQKUR3JACxlF6ACGizQnc7sDg57/sBYr1SDZmUceGIJ+BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T13:50:41.910925Z","bundle_sha256":"45e043226d7e27737fea8954a451bc3db96028a8c68d9b0727f6d13ce1bde778"}}