{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RHYKOEIXT2WZYUB75JN6DJBAQ5","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":"ec5005aada68fbdb97f73fca065072a09465b1a7f6c3da711fb36e14f749d683","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T16:32:31Z","title_canon_sha256":"00509cf2364516344ff8be08b28af3bab095686fd5e8de5b38a50651d143049e"},"schema_version":"1.0","source":{"id":"2506.08961","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08961","created_at":"2026-07-05T11:19:16Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08961v1","created_at":"2026-07-05T11:19:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08961","created_at":"2026-07-05T11:19:16Z"},{"alias_kind":"pith_short_12","alias_value":"RHYKOEIXT2WZ","created_at":"2026-07-05T11:19:16Z"},{"alias_kind":"pith_short_16","alias_value":"RHYKOEIXT2WZYUB7","created_at":"2026-07-05T11:19:16Z"},{"alias_kind":"pith_short_8","alias_value":"RHYKOEIX","created_at":"2026-07-05T11:19:16Z"}],"graph_snapshots":[{"event_id":"sha256:e138bf560589a30a68186854282ddc5fa07124645f88f2d92c2b759ab78b4aa5","target":"graph","created_at":"2026-07-05T11:19:16Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.08961/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adversarial attacks and robustness in Deep Reinforcement Learning (DRL) have been widely studied in various threat models; however, few consider environmental state perturbations, which are natural in embodied scenarios. To improve the robustness of DRL agents, we formulate the problem of environmental state perturbation, introducing a preliminary non-targeted attack method as a calibration adversary, and then propose a defense framework, named Boosted Adversarial Training (BAT), which first tunes the agents via supervised learning to avoid catastrophic failure and subsequently adversarially t","authors_text":"Chenxu Wang, Huaping Liu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T16:32:31Z","title":"Towards Robust Deep Reinforcement Learning against Environmental State Perturbation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08961","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:e12e7b0963fb952739f607ef1ba72e85cc8636d2225464fc07b04b3408ee75a5","target":"record","created_at":"2026-07-05T11:19:16Z","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":"ec5005aada68fbdb97f73fca065072a09465b1a7f6c3da711fb36e14f749d683","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T16:32:31Z","title_canon_sha256":"00509cf2364516344ff8be08b28af3bab095686fd5e8de5b38a50651d143049e"},"schema_version":"1.0","source":{"id":"2506.08961","kind":"arxiv","version":1}},"canonical_sha256":"89f0a711179ead9c503fea5be1a42087575e12ae26d61ab1c71af255bc548711","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89f0a711179ead9c503fea5be1a42087575e12ae26d61ab1c71af255bc548711","first_computed_at":"2026-07-05T11:19:16.014482Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:16.014482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SqMNagUrf0QqHUlrgU7UDoiZJPg6DglYjLlk0RqF19WHxJhqI7FDs8mBDZ165SLeb3tayl5hCy3xpFGbcfL6Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:16.014977Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.08961","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e12e7b0963fb952739f607ef1ba72e85cc8636d2225464fc07b04b3408ee75a5","sha256:e138bf560589a30a68186854282ddc5fa07124645f88f2d92c2b759ab78b4aa5"],"state_sha256":"a74f3b03170e9db47e423bd00df8c346b576801736213369230a2906fc392cdd"}