{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:DPRVM74NWXIISL4EZMY3KUMEVE","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":"e672970894382258d7fa936991599e6b3a968738a45ff413a258cb54d1f087f7","cross_cats_sorted":["cs.AI","cs.CR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-28T23:22:28Z","title_canon_sha256":"9a19f7822c6817fe6483f6e47f6cb39f579fad5262cfeb94a1d3f7cb0713fd29"},"schema_version":"1.0","source":{"id":"2003.12909","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.12909","created_at":"2026-07-05T01:28:19Z"},{"alias_kind":"arxiv_version","alias_value":"2003.12909v2","created_at":"2026-07-05T01:28:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.12909","created_at":"2026-07-05T01:28:19Z"},{"alias_kind":"pith_short_12","alias_value":"DPRVM74NWXII","created_at":"2026-07-05T01:28:19Z"},{"alias_kind":"pith_short_16","alias_value":"DPRVM74NWXIISL4E","created_at":"2026-07-05T01:28:19Z"},{"alias_kind":"pith_short_8","alias_value":"DPRVM74N","created_at":"2026-07-05T01:28:19Z"}],"graph_snapshots":[{"event_id":"sha256:c575a89f0927fb717ef8916c455d4df376d9ba83cecfc9ad1f71e884d0666deb","target":"graph","created_at":"2026-07-05T01:28:19Z","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/2003.12909/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study a security threat to reinforcement learning where an attacker poisons the learning environment to force the agent into executing a target policy chosen by the attacker. As a victim, we consider RL agents whose objective is to find a policy that maximizes average reward in undiscounted infinite-horizon problem settings. The attacker can manipulate the rewards or the transition dynamics in the learning environment at training-time and is interested in doing so in a stealthy manner. We propose an optimization framework for finding an \\emph{optimal stealthy attack} for different measures ","authors_text":"Adish Singla, Amin Rakhsha, Goran Radanovic, Rati Devidze, Xiaojin Zhu","cross_cats":["cs.AI","cs.CR","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-28T23:22:28Z","title":"Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.12909","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":"sha256:82dab636439605beb135e8ffb2407714a545ed6779e885b06a541bcc76f162a8","target":"record","created_at":"2026-07-05T01:28:19Z","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":"e672970894382258d7fa936991599e6b3a968738a45ff413a258cb54d1f087f7","cross_cats_sorted":["cs.AI","cs.CR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-28T23:22:28Z","title_canon_sha256":"9a19f7822c6817fe6483f6e47f6cb39f579fad5262cfeb94a1d3f7cb0713fd29"},"schema_version":"1.0","source":{"id":"2003.12909","kind":"arxiv","version":2}},"canonical_sha256":"1be3567f8db5d0892f84cb31b55184a93ea54b3912d130b03cc7841c651b8bec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1be3567f8db5d0892f84cb31b55184a93ea54b3912d130b03cc7841c651b8bec","first_computed_at":"2026-07-05T01:28:19.509956Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:28:19.509956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TL5Q3cqULS7qyUsks4ZCxmSJagBa5j49wW45vcxRReCX+/h0NlyNI5kcYvSdyBs2LgLcWMsb+q7/FyXXsZ8gAA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:28:19.510282Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.12909","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:82dab636439605beb135e8ffb2407714a545ed6779e885b06a541bcc76f162a8","sha256:c575a89f0927fb717ef8916c455d4df376d9ba83cecfc9ad1f71e884d0666deb"],"state_sha256":"0c3dc7f5b64173ee66b7c75967d5fe6b28964e27a76a1c3b7c850c32b1e5fda6"}