{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:YZSVZQHIYMSQYGP3CTW52IBSEW","short_pith_number":"pith:YZSVZQHI","canonical_record":{"source":{"id":"2306.07408","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-12T20:21:40Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"e64d6ab4ee10bfb1ad7285ef01b19f4c92e2874af34aa652b94433aa41a8729b","abstract_canon_sha256":"f0f8fff28e27a802bf41185ac13e306fdf5d5c342bf42c11589633184b55c952"},"schema_version":"1.0"},"canonical_sha256":"c6655cc0e8c3250c19fb14eddd203225b85bc58b8442e40d72b5c50b5762422c","source":{"kind":"arxiv","id":"2306.07408","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.07408","created_at":"2026-07-05T06:20:03Z"},{"alias_kind":"arxiv_version","alias_value":"2306.07408v1","created_at":"2026-07-05T06:20:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07408","created_at":"2026-07-05T06:20:03Z"},{"alias_kind":"pith_short_12","alias_value":"YZSVZQHIYMSQ","created_at":"2026-07-05T06:20:03Z"},{"alias_kind":"pith_short_16","alias_value":"YZSVZQHIYMSQYGP3","created_at":"2026-07-05T06:20:03Z"},{"alias_kind":"pith_short_8","alias_value":"YZSVZQHI","created_at":"2026-07-05T06:20:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:YZSVZQHIYMSQYGP3CTW52IBSEW","target":"record","payload":{"canonical_record":{"source":{"id":"2306.07408","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-12T20:21:40Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"e64d6ab4ee10bfb1ad7285ef01b19f4c92e2874af34aa652b94433aa41a8729b","abstract_canon_sha256":"f0f8fff28e27a802bf41185ac13e306fdf5d5c342bf42c11589633184b55c952"},"schema_version":"1.0"},"canonical_sha256":"c6655cc0e8c3250c19fb14eddd203225b85bc58b8442e40d72b5c50b5762422c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:20:03.660387Z","signature_b64":"KSI/8hPmC1FJDlJKzxB2nkNxb+upPll55uy478PHYTq1SetTPDD2+v6cXm1o3gIvBNmwipyLXb0kDeD5b0cdBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6655cc0e8c3250c19fb14eddd203225b85bc58b8442e40d72b5c50b5762422c","last_reissued_at":"2026-07-05T06:20:03.659914Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:20:03.659914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.07408","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":"2026-07-05T06:20:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E+VSmeWD0oob8tjcwFERPq9l4pmOLSKwAkqG+KeRtW5Vnaz/QguYo62whoiOAn+QAKeTJWbjtNtNt4o0sKLPBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T13:25:21.727074Z"},"content_sha256":"2feb0b11d758d05e92dd1d7faf76a8bbf2fcef099224faa0e5deadfe55c84266","schema_version":"1.0","event_id":"sha256:2feb0b11d758d05e92dd1d7faf76a8bbf2fcef099224faa0e5deadfe55c84266"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:YZSVZQHIYMSQYGP3CTW52IBSEW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Reinforcement Learning through Efficient Adversarial Herding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Hao-Lun Hsu, Juncheng Dong, Miroslav Pajic, Qitong Gao, Vahid Tarokh","submitted_at":"2023-06-12T20:21:40Z","abstract_excerpt":"Although reinforcement learning (RL) is considered the gold standard for policy design, it may not always provide a robust solution in various scenarios. This can result in severe performance degradation when the environment is exposed to potential disturbances. Adversarial training using a two-player max-min game has been proven effective in enhancing the robustness of RL agents. In this work, we extend the two-player game by introducing an adversarial herd, which involves a group of adversaries, in order to address ($\\textit{i}$) the difficulty of the inner optimization problem, and ($\\texti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07408","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2306.07408/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":"2026-07-05T06:20:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kxOYFOETAYuA8WY164/lxUOSsJaONYwiibv2pBPtKEzr8HlDPiNkKsnHBpAghOwpLROKX2WsNHtkwFTXB3JBCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T13:25:21.728995Z"},"content_sha256":"ec312492b28bfdeb25ffd3c785199a817bf54a82b1c6f4a4535bfe409450e188","schema_version":"1.0","event_id":"sha256:ec312492b28bfdeb25ffd3c785199a817bf54a82b1c6f4a4535bfe409450e188"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YZSVZQHIYMSQYGP3CTW52IBSEW/bundle.json","state_url":"https://pith.science/pith/YZSVZQHIYMSQYGP3CTW52IBSEW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YZSVZQHIYMSQYGP3CTW52IBSEW/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":"2026-08-10T13:25:21Z","links":{"resolver":"https://pith.science/pith/YZSVZQHIYMSQYGP3CTW52IBSEW","bundle":"https://pith.science/pith/YZSVZQHIYMSQYGP3CTW52IBSEW/bundle.json","state":"https://pith.science/pith/YZSVZQHIYMSQYGP3CTW52IBSEW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YZSVZQHIYMSQYGP3CTW52IBSEW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YZSVZQHIYMSQYGP3CTW52IBSEW","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":"f0f8fff28e27a802bf41185ac13e306fdf5d5c342bf42c11589633184b55c952","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-12T20:21:40Z","title_canon_sha256":"e64d6ab4ee10bfb1ad7285ef01b19f4c92e2874af34aa652b94433aa41a8729b"},"schema_version":"1.0","source":{"id":"2306.07408","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.07408","created_at":"2026-07-05T06:20:03Z"},{"alias_kind":"arxiv_version","alias_value":"2306.07408v1","created_at":"2026-07-05T06:20:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07408","created_at":"2026-07-05T06:20:03Z"},{"alias_kind":"pith_short_12","alias_value":"YZSVZQHIYMSQ","created_at":"2026-07-05T06:20:03Z"},{"alias_kind":"pith_short_16","alias_value":"YZSVZQHIYMSQYGP3","created_at":"2026-07-05T06:20:03Z"},{"alias_kind":"pith_short_8","alias_value":"YZSVZQHI","created_at":"2026-07-05T06:20:03Z"}],"graph_snapshots":[{"event_id":"sha256:ec312492b28bfdeb25ffd3c785199a817bf54a82b1c6f4a4535bfe409450e188","target":"graph","created_at":"2026-07-05T06:20:03Z","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/2306.07408/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although reinforcement learning (RL) is considered the gold standard for policy design, it may not always provide a robust solution in various scenarios. This can result in severe performance degradation when the environment is exposed to potential disturbances. Adversarial training using a two-player max-min game has been proven effective in enhancing the robustness of RL agents. In this work, we extend the two-player game by introducing an adversarial herd, which involves a group of adversaries, in order to address ($\\textit{i}$) the difficulty of the inner optimization problem, and ($\\texti","authors_text":"Hao-Lun Hsu, Juncheng Dong, Miroslav Pajic, Qitong Gao, Vahid Tarokh","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-12T20:21:40Z","title":"Robust Reinforcement Learning through Efficient Adversarial Herding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07408","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":"sha256:2feb0b11d758d05e92dd1d7faf76a8bbf2fcef099224faa0e5deadfe55c84266","target":"record","created_at":"2026-07-05T06:20:03Z","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":"f0f8fff28e27a802bf41185ac13e306fdf5d5c342bf42c11589633184b55c952","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-12T20:21:40Z","title_canon_sha256":"e64d6ab4ee10bfb1ad7285ef01b19f4c92e2874af34aa652b94433aa41a8729b"},"schema_version":"1.0","source":{"id":"2306.07408","kind":"arxiv","version":1}},"canonical_sha256":"c6655cc0e8c3250c19fb14eddd203225b85bc58b8442e40d72b5c50b5762422c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6655cc0e8c3250c19fb14eddd203225b85bc58b8442e40d72b5c50b5762422c","first_computed_at":"2026-07-05T06:20:03.659914Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:20:03.659914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KSI/8hPmC1FJDlJKzxB2nkNxb+upPll55uy478PHYTq1SetTPDD2+v6cXm1o3gIvBNmwipyLXb0kDeD5b0cdBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:20:03.660387Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.07408","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2feb0b11d758d05e92dd1d7faf76a8bbf2fcef099224faa0e5deadfe55c84266","sha256:ec312492b28bfdeb25ffd3c785199a817bf54a82b1c6f4a4535bfe409450e188"],"state_sha256":"e18e2fc185e32c9970a41fde425c9465cacc38f1ed9edf00e3ab3b68d6c1526e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O3IkxREf3qyvOiSlT6cxLgs44xSD/7wyjMi1zrEQsBE80y1Qr+28NG8lxi/QDIBrzJIUJdKddI74H/XDaWOrCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T13:25:21.734114Z","bundle_sha256":"f81f0c3e08cfd93afb136b9c8288245c302c2580567653974978fad6e7b9d127"}}