{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:EMWZNIW5E3DFYIHU2BUGOWDFBB","short_pith_number":"pith:EMWZNIW5","schema_version":"1.0","canonical_sha256":"232d96a2dd26c65c20f4d0686758650862c41672c0a217886fca54cabe9f6707","source":{"kind":"arxiv","id":"1904.01318","version":1},"attestation_state":"computed","paper":{"title":"Finding and Visualizing Weaknesses of Deep Reinforcement Learning Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christian Rupprecht, Christopher J. Pal, Cyril Ibrahim","submitted_at":"2019-04-02T10:21:23Z","abstract_excerpt":"As deep reinforcement learning driven by visual perception becomes more widely used there is a growing need to better understand and probe the learned agents. Understanding the decision making process and its relationship to visual inputs can be very valuable to identify problems in learned behavior. However, this topic has been relatively under-explored in the research community. In this work we present a method for synthesizing visual inputs of interest for a trained agent. Such inputs or states could be situations in which specific actions are necessary. Further, critical states in which a "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1904.01318","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-02T10:21:23Z","cross_cats_sorted":[],"title_canon_sha256":"d2749cff318adfe66f206ced97c43b4c348b3f895192b23ed73820663d53d5a3","abstract_canon_sha256":"1980153676d77050f251bcde67d71317c9e79e25b5cbd389fe94e3d11170ecf1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:35.101558Z","signature_b64":"RhO8Ooq0TcCqkpE9AE2f0fw7kaI9UMukhSfCfePeuoh091STp/sxnlCbUjXQgcXWOL2H0rDkEdhOZRQrFKixDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"232d96a2dd26c65c20f4d0686758650862c41672c0a217886fca54cabe9f6707","last_reissued_at":"2026-05-17T23:49:35.100942Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:35.100942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Finding and Visualizing Weaknesses of Deep Reinforcement Learning Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christian Rupprecht, Christopher J. Pal, Cyril Ibrahim","submitted_at":"2019-04-02T10:21:23Z","abstract_excerpt":"As deep reinforcement learning driven by visual perception becomes more widely used there is a growing need to better understand and probe the learned agents. Understanding the decision making process and its relationship to visual inputs can be very valuable to identify problems in learned behavior. However, this topic has been relatively under-explored in the research community. In this work we present a method for synthesizing visual inputs of interest for a trained agent. Such inputs or states could be situations in which specific actions are necessary. Further, critical states in which a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.01318","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1904.01318","created_at":"2026-05-17T23:49:35.101026+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.01318v1","created_at":"2026-05-17T23:49:35.101026+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.01318","created_at":"2026-05-17T23:49:35.101026+00:00"},{"alias_kind":"pith_short_12","alias_value":"EMWZNIW5E3DF","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"EMWZNIW5E3DFYIHU","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"EMWZNIW5","created_at":"2026-05-18T12:33:15.570797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EMWZNIW5E3DFYIHU2BUGOWDFBB","json":"https://pith.science/pith/EMWZNIW5E3DFYIHU2BUGOWDFBB.json","graph_json":"https://pith.science/api/pith-number/EMWZNIW5E3DFYIHU2BUGOWDFBB/graph.json","events_json":"https://pith.science/api/pith-number/EMWZNIW5E3DFYIHU2BUGOWDFBB/events.json","paper":"https://pith.science/paper/EMWZNIW5"},"agent_actions":{"view_html":"https://pith.science/pith/EMWZNIW5E3DFYIHU2BUGOWDFBB","download_json":"https://pith.science/pith/EMWZNIW5E3DFYIHU2BUGOWDFBB.json","view_paper":"https://pith.science/paper/EMWZNIW5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.01318&json=true","fetch_graph":"https://pith.science/api/pith-number/EMWZNIW5E3DFYIHU2BUGOWDFBB/graph.json","fetch_events":"https://pith.science/api/pith-number/EMWZNIW5E3DFYIHU2BUGOWDFBB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EMWZNIW5E3DFYIHU2BUGOWDFBB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EMWZNIW5E3DFYIHU2BUGOWDFBB/action/storage_attestation","attest_author":"https://pith.science/pith/EMWZNIW5E3DFYIHU2BUGOWDFBB/action/author_attestation","sign_citation":"https://pith.science/pith/EMWZNIW5E3DFYIHU2BUGOWDFBB/action/citation_signature","submit_replication":"https://pith.science/pith/EMWZNIW5E3DFYIHU2BUGOWDFBB/action/replication_record"}},"created_at":"2026-05-17T23:49:35.101026+00:00","updated_at":"2026-05-17T23:49:35.101026+00:00"}