{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:EWH2U6ELV3RJKR4FCB2AVOW5EM","short_pith_number":"pith:EWH2U6EL","canonical_record":{"source":{"id":"1901.09184","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-26T09:37:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0e548d087250cbe0bd1d48dacaf27027be87d689e0c84293cc6aa41bb5e261a3","abstract_canon_sha256":"bdfa29f95f2d938181088aa9a989acecca92ebed1019f1311ce0e0d30edf58ad"},"schema_version":"1.0"},"canonical_sha256":"258faa788baee295478510740abadd2327b796920fba20ceb1c4d050c483512b","source":{"kind":"arxiv","id":"1901.09184","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.09184","created_at":"2026-05-17T23:46:52Z"},{"alias_kind":"arxiv_version","alias_value":"1901.09184v2","created_at":"2026-05-17T23:46:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.09184","created_at":"2026-05-17T23:46:52Z"},{"alias_kind":"pith_short_12","alias_value":"EWH2U6ELV3RJ","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"EWH2U6ELV3RJKR4F","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"EWH2U6EL","created_at":"2026-05-18T12:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:EWH2U6ELV3RJKR4FCB2AVOW5EM","target":"record","payload":{"canonical_record":{"source":{"id":"1901.09184","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-26T09:37:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0e548d087250cbe0bd1d48dacaf27027be87d689e0c84293cc6aa41bb5e261a3","abstract_canon_sha256":"bdfa29f95f2d938181088aa9a989acecca92ebed1019f1311ce0e0d30edf58ad"},"schema_version":"1.0"},"canonical_sha256":"258faa788baee295478510740abadd2327b796920fba20ceb1c4d050c483512b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:52.986431Z","signature_b64":"Tgg2GIbE5hTqBMTbSzXjGXlDiB77H7KLVmesFaFtxYkq5tv1dgVPXjvUKzm/6ZFyw1YB0eZzLCLJzUBKXNTyAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"258faa788baee295478510740abadd2327b796920fba20ceb1c4d050c483512b","last_reissued_at":"2026-05-17T23:46:52.985849Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:52.985849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.09184","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":"2026-05-17T23:46:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tzGtetBRSLNbv7HufUJ4qfWMR1oke3k+RmWvi4d+beng8nbvrQAZ1O8xXJPU+7YLpKnJm1zBBPB3ia4RzgvyCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T01:10:30.909105Z"},"content_sha256":"264846ad8f110a718a94d4200b10278de1d03f417eaeba9f1ec131f1086ad6d8","schema_version":"1.0","event_id":"sha256:264846ad8f110a718a94d4200b10278de1d03f417eaeba9f1ec131f1086ad6d8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:EWH2U6ELV3RJKR4FCB2AVOW5EM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Action Robust Reinforcement Learning and Applications in Continuous Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chen Tessler, Shie Mannor, Yonathan Efroni","submitted_at":"2019-01-26T09:37:53Z","abstract_excerpt":"A policy is said to be robust if it maximizes the reward while considering a bad, or even adversarial, model. In this work we formalize two new criteria of robustness to action uncertainty. Specifically, we consider two scenarios in which the agent attempts to perform an action $a$, and (i) with probability $\\alpha$, an alternative adversarial action $\\bar a$ is taken, or (ii) an adversary adds a perturbation to the selected action in the case of continuous action space. We show that our criteria are related to common forms of uncertainty in robotics domains, such as the occurrence of abrupt f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.09184","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":"2026-05-17T23:46:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7AxXYvYZTaXyoNhAkSrSmu7PYv1s3vtPEO+FgqF6RX3pCN7EMjszZNlwQ1tpUz1c8BcsZ9MqhGTsksr2YoRiBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T01:10:30.909855Z"},"content_sha256":"7d70255ca4056de4bfbdd21c80ccc561f955ce36b091fad31816dacaf6a28a2a","schema_version":"1.0","event_id":"sha256:7d70255ca4056de4bfbdd21c80ccc561f955ce36b091fad31816dacaf6a28a2a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EWH2U6ELV3RJKR4FCB2AVOW5EM/bundle.json","state_url":"https://pith.science/pith/EWH2U6ELV3RJKR4FCB2AVOW5EM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EWH2U6ELV3RJKR4FCB2AVOW5EM/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":"2026-05-27T01:10:30Z","links":{"resolver":"https://pith.science/pith/EWH2U6ELV3RJKR4FCB2AVOW5EM","bundle":"https://pith.science/pith/EWH2U6ELV3RJKR4FCB2AVOW5EM/bundle.json","state":"https://pith.science/pith/EWH2U6ELV3RJKR4FCB2AVOW5EM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EWH2U6ELV3RJKR4FCB2AVOW5EM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:EWH2U6ELV3RJKR4FCB2AVOW5EM","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":"bdfa29f95f2d938181088aa9a989acecca92ebed1019f1311ce0e0d30edf58ad","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-26T09:37:53Z","title_canon_sha256":"0e548d087250cbe0bd1d48dacaf27027be87d689e0c84293cc6aa41bb5e261a3"},"schema_version":"1.0","source":{"id":"1901.09184","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.09184","created_at":"2026-05-17T23:46:52Z"},{"alias_kind":"arxiv_version","alias_value":"1901.09184v2","created_at":"2026-05-17T23:46:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.09184","created_at":"2026-05-17T23:46:52Z"},{"alias_kind":"pith_short_12","alias_value":"EWH2U6ELV3RJ","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"EWH2U6ELV3RJKR4F","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"EWH2U6EL","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:7d70255ca4056de4bfbdd21c80ccc561f955ce36b091fad31816dacaf6a28a2a","target":"graph","created_at":"2026-05-17T23:46:52Z","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":"A policy is said to be robust if it maximizes the reward while considering a bad, or even adversarial, model. In this work we formalize two new criteria of robustness to action uncertainty. Specifically, we consider two scenarios in which the agent attempts to perform an action $a$, and (i) with probability $\\alpha$, an alternative adversarial action $\\bar a$ is taken, or (ii) an adversary adds a perturbation to the selected action in the case of continuous action space. We show that our criteria are related to common forms of uncertainty in robotics domains, such as the occurrence of abrupt f","authors_text":"Chen Tessler, Shie Mannor, Yonathan Efroni","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-26T09:37:53Z","title":"Action Robust Reinforcement Learning and Applications in Continuous Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.09184","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":"sha256:264846ad8f110a718a94d4200b10278de1d03f417eaeba9f1ec131f1086ad6d8","target":"record","created_at":"2026-05-17T23:46:52Z","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":"bdfa29f95f2d938181088aa9a989acecca92ebed1019f1311ce0e0d30edf58ad","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-26T09:37:53Z","title_canon_sha256":"0e548d087250cbe0bd1d48dacaf27027be87d689e0c84293cc6aa41bb5e261a3"},"schema_version":"1.0","source":{"id":"1901.09184","kind":"arxiv","version":2}},"canonical_sha256":"258faa788baee295478510740abadd2327b796920fba20ceb1c4d050c483512b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"258faa788baee295478510740abadd2327b796920fba20ceb1c4d050c483512b","first_computed_at":"2026-05-17T23:46:52.985849Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:52.985849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Tgg2GIbE5hTqBMTbSzXjGXlDiB77H7KLVmesFaFtxYkq5tv1dgVPXjvUKzm/6ZFyw1YB0eZzLCLJzUBKXNTyAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:52.986431Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.09184","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:264846ad8f110a718a94d4200b10278de1d03f417eaeba9f1ec131f1086ad6d8","sha256:7d70255ca4056de4bfbdd21c80ccc561f955ce36b091fad31816dacaf6a28a2a"],"state_sha256":"6f48b42045dd22481affe113695047ded2055967e8c101c72e12c2ad014cf497"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jFhSEgMExJfD422pq6aSuQabSYleIUsi6VjZuNTPMocixpCCR4GCRcj5Gz1Xvr9WTuUik0tyWH7UOxC1belnDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T01:10:30.913961Z","bundle_sha256":"6d7defdc52027125fced4f3530e733c070a9e196055d79d4a12dda769f96e3b5"}}