{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:ENXSUBFMR7QO6RE7TQBTDYKJK3","short_pith_number":"pith:ENXSUBFM","canonical_record":{"source":{"id":"1712.03632","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-11T02:58:13Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"e636c379d8189d7cdc6779d9e806fb60ca44974e1efa4337b5c3653b56f38fcc","abstract_canon_sha256":"475f4eefc213111b0aba4e91e4ec4c8000180f53015a138835bd778336ea4724"},"schema_version":"1.0"},"canonical_sha256":"236f2a04ac8fe0ef449f9c0331e14956d8257fc89e64162365c45a8acb288ace","source":{"kind":"arxiv","id":"1712.03632","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.03632","created_at":"2026-05-18T00:28:20Z"},{"alias_kind":"arxiv_version","alias_value":"1712.03632v1","created_at":"2026-05-18T00:28:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.03632","created_at":"2026-05-18T00:28:20Z"},{"alias_kind":"pith_short_12","alias_value":"ENXSUBFMR7QO","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"ENXSUBFMR7QO6RE7","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"ENXSUBFM","created_at":"2026-05-18T12:31:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:ENXSUBFMR7QO6RE7TQBTDYKJK3","target":"record","payload":{"canonical_record":{"source":{"id":"1712.03632","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-11T02:58:13Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"e636c379d8189d7cdc6779d9e806fb60ca44974e1efa4337b5c3653b56f38fcc","abstract_canon_sha256":"475f4eefc213111b0aba4e91e4ec4c8000180f53015a138835bd778336ea4724"},"schema_version":"1.0"},"canonical_sha256":"236f2a04ac8fe0ef449f9c0331e14956d8257fc89e64162365c45a8acb288ace","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:20.521926Z","signature_b64":"FuXGgfUeJfHSF7f3+GjB+iNTvEZto8zP2rcyLTl0vzKO2Bq92vNxcbQqHO0Pd56YIDhC6DNsmKLB4lSgoCx9AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"236f2a04ac8fe0ef449f9c0331e14956d8257fc89e64162365c45a8acb288ace","last_reissued_at":"2026-05-18T00:28:20.521209Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:20.521209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.03632","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":"2026-05-18T00:28:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DD+ibncyGnOhUEgKxhGaGoZ0COWsdh4IznXEXqSM7LNQDTXfd6NWCRhWAqfM3/w5+NEwFZlrvW1RuspoOhgpDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T19:55:53.737279Z"},"content_sha256":"92636f8391ccc6937b52710e5a75d1f488da381db5d7a26cd2c77281f924dabb","schema_version":"1.0","event_id":"sha256:92636f8391ccc6937b52710e5a75d1f488da381db5d7a26cd2c77281f924dabb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:ENXSUBFMR7QO6RE7TQBTDYKJK3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Deep Reinforcement Learning with Adversarial Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Anay Pattanaik, Gautham Bommannan, Girish Chowdhary, Shuijing Liu, Zhenyi Tang","submitted_at":"2017-12-11T02:58:13Z","abstract_excerpt":"This paper proposes adversarial attacks for Reinforcement Learning (RL) and then improves the robustness of Deep Reinforcement Learning algorithms (DRL) to parameter uncertainties with the help of these attacks. We show that even a naively engineered attack successfully degrades the performance of DRL algorithm. We further improve the attack using gradient information of an engineered loss function which leads to further degradation in performance. These attacks are then leveraged during training to improve the robustness of RL within robust control framework. We show that this adversarial tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.03632","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":""},"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":"2026-05-18T00:28:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0806keYlGALqhpPJwe2l1dkJEMfzc9/CXoihWWjdgZ6XjFnJsKr4dn6twISyVRhWcC6ClbFpx3QYVPr04RU+BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T19:55:53.737960Z"},"content_sha256":"d8a5c2dd058ec365a5c4f42579a969b9c6969703b637213f0dbed496027939b8","schema_version":"1.0","event_id":"sha256:d8a5c2dd058ec365a5c4f42579a969b9c6969703b637213f0dbed496027939b8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ENXSUBFMR7QO6RE7TQBTDYKJK3/bundle.json","state_url":"https://pith.science/pith/ENXSUBFMR7QO6RE7TQBTDYKJK3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ENXSUBFMR7QO6RE7TQBTDYKJK3/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":"2026-05-28T19:55:53Z","links":{"resolver":"https://pith.science/pith/ENXSUBFMR7QO6RE7TQBTDYKJK3","bundle":"https://pith.science/pith/ENXSUBFMR7QO6RE7TQBTDYKJK3/bundle.json","state":"https://pith.science/pith/ENXSUBFMR7QO6RE7TQBTDYKJK3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ENXSUBFMR7QO6RE7TQBTDYKJK3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:ENXSUBFMR7QO6RE7TQBTDYKJK3","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":"475f4eefc213111b0aba4e91e4ec4c8000180f53015a138835bd778336ea4724","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-11T02:58:13Z","title_canon_sha256":"e636c379d8189d7cdc6779d9e806fb60ca44974e1efa4337b5c3653b56f38fcc"},"schema_version":"1.0","source":{"id":"1712.03632","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.03632","created_at":"2026-05-18T00:28:20Z"},{"alias_kind":"arxiv_version","alias_value":"1712.03632v1","created_at":"2026-05-18T00:28:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.03632","created_at":"2026-05-18T00:28:20Z"},{"alias_kind":"pith_short_12","alias_value":"ENXSUBFMR7QO","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"ENXSUBFMR7QO6RE7","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"ENXSUBFM","created_at":"2026-05-18T12:31:12Z"}],"graph_snapshots":[{"event_id":"sha256:d8a5c2dd058ec365a5c4f42579a969b9c6969703b637213f0dbed496027939b8","target":"graph","created_at":"2026-05-18T00:28:20Z","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":"This paper proposes adversarial attacks for Reinforcement Learning (RL) and then improves the robustness of Deep Reinforcement Learning algorithms (DRL) to parameter uncertainties with the help of these attacks. We show that even a naively engineered attack successfully degrades the performance of DRL algorithm. We further improve the attack using gradient information of an engineered loss function which leads to further degradation in performance. These attacks are then leveraged during training to improve the robustness of RL within robust control framework. We show that this adversarial tra","authors_text":"Anay Pattanaik, Gautham Bommannan, Girish Chowdhary, Shuijing Liu, Zhenyi Tang","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-11T02:58:13Z","title":"Robust Deep Reinforcement Learning with Adversarial Attacks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.03632","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":"sha256:92636f8391ccc6937b52710e5a75d1f488da381db5d7a26cd2c77281f924dabb","target":"record","created_at":"2026-05-18T00:28:20Z","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":"475f4eefc213111b0aba4e91e4ec4c8000180f53015a138835bd778336ea4724","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-11T02:58:13Z","title_canon_sha256":"e636c379d8189d7cdc6779d9e806fb60ca44974e1efa4337b5c3653b56f38fcc"},"schema_version":"1.0","source":{"id":"1712.03632","kind":"arxiv","version":1}},"canonical_sha256":"236f2a04ac8fe0ef449f9c0331e14956d8257fc89e64162365c45a8acb288ace","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"236f2a04ac8fe0ef449f9c0331e14956d8257fc89e64162365c45a8acb288ace","first_computed_at":"2026-05-18T00:28:20.521209Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:28:20.521209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FuXGgfUeJfHSF7f3+GjB+iNTvEZto8zP2rcyLTl0vzKO2Bq92vNxcbQqHO0Pd56YIDhC6DNsmKLB4lSgoCx9AA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:28:20.521926Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.03632","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92636f8391ccc6937b52710e5a75d1f488da381db5d7a26cd2c77281f924dabb","sha256:d8a5c2dd058ec365a5c4f42579a969b9c6969703b637213f0dbed496027939b8"],"state_sha256":"27f2a99320e9e6bd4f93c6f5c7c3ae0c10c2e556d51fcbca85360daeba2ba832"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mg8FmyulcVLVtFNKojAIzqDqu7jP9OTGe6mSsQRdhuHoz0XyqyzAy3NJ90Ff2+7RZNkqComxMn/MYNF/vKR7AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T19:55:53.741554Z","bundle_sha256":"11b89c9ef9227faebcc74a6640fe21e8efb77ccb893dbee39740c802aa10f3ab"}}