{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6JKNKKOIIV3ECCDMKN234OPU2R","short_pith_number":"pith:6JKNKKOI","schema_version":"1.0","canonical_sha256":"f254d529c8457641086c5375be39f4d47f275216b84f58e0df77e29f2b81603c","source":{"kind":"arxiv","id":"2202.12180","version":3},"attestation_state":"computed","paper":{"title":"Quantum Deep Reinforcement Learning for Robot Navigation Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","quant-ph"],"primary_cat":"cs.RO","authors_text":"Dirk Heimann, Felix Wiebe, Frank Kirchner, Hans Hohenfeld","submitted_at":"2022-02-24T16:26:23Z","abstract_excerpt":"We utilize hybrid quantum deep reinforcement learning to learn navigation tasks for a simple, wheeled robot in simulated environments of increasing complexity. For this, we train parameterized quantum circuits (PQCs) with two different encoding strategies in a hybrid quantum-classical setup as well as a classical neural network baseline with the double deep Q network (DDQN) reinforcement learning algorithm. Quantum deep reinforcement learning (QDRL) has previously been studied in several relatively simple benchmark environments, mainly from the OpenAI gym suite. However, scaling behavior and 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":"2202.12180","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-02-24T16:26:23Z","cross_cats_sorted":["cs.LG","quant-ph"],"title_canon_sha256":"90d96af2f7a5a95245d1217748a03e00f3b227dd29fe8786eea3fadbf069b011","abstract_canon_sha256":"5c6f120117d9d6a0a2d75a2b0a342eaee3d08492b84aae18691d2ec7f37d7a42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:33.079270Z","signature_b64":"hSWbgOGlSeB8Cnc/uPfZprcccyRBBgtO0jn0fBqFU9pWV20POM7ik38kE5xRTrdK8KsEVzQw3eEacm2PQ2A2CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f254d529c8457641086c5375be39f4d47f275216b84f58e0df77e29f2b81603c","last_reissued_at":"2026-07-05T08:35:33.078860Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:33.078860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantum Deep Reinforcement Learning for Robot Navigation Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","quant-ph"],"primary_cat":"cs.RO","authors_text":"Dirk Heimann, Felix Wiebe, Frank Kirchner, Hans Hohenfeld","submitted_at":"2022-02-24T16:26:23Z","abstract_excerpt":"We utilize hybrid quantum deep reinforcement learning to learn navigation tasks for a simple, wheeled robot in simulated environments of increasing complexity. For this, we train parameterized quantum circuits (PQCs) with two different encoding strategies in a hybrid quantum-classical setup as well as a classical neural network baseline with the double deep Q network (DDQN) reinforcement learning algorithm. Quantum deep reinforcement learning (QDRL) has previously been studied in several relatively simple benchmark environments, mainly from the OpenAI gym suite. However, scaling behavior and a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.12180","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2202.12180/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2202.12180","created_at":"2026-07-05T08:35:33.078916+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.12180v3","created_at":"2026-07-05T08:35:33.078916+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.12180","created_at":"2026-07-05T08:35:33.078916+00:00"},{"alias_kind":"pith_short_12","alias_value":"6JKNKKOIIV3E","created_at":"2026-07-05T08:35:33.078916+00:00"},{"alias_kind":"pith_short_16","alias_value":"6JKNKKOIIV3ECCDM","created_at":"2026-07-05T08:35:33.078916+00:00"},{"alias_kind":"pith_short_8","alias_value":"6JKNKKOI","created_at":"2026-07-05T08:35:33.078916+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.21246","citing_title":"HCQA: Hybrid Classical-Quantum Agent for Generating Optimal Quantum Sensor Circuits","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6JKNKKOIIV3ECCDMKN234OPU2R","json":"https://pith.science/pith/6JKNKKOIIV3ECCDMKN234OPU2R.json","graph_json":"https://pith.science/api/pith-number/6JKNKKOIIV3ECCDMKN234OPU2R/graph.json","events_json":"https://pith.science/api/pith-number/6JKNKKOIIV3ECCDMKN234OPU2R/events.json","paper":"https://pith.science/paper/6JKNKKOI"},"agent_actions":{"view_html":"https://pith.science/pith/6JKNKKOIIV3ECCDMKN234OPU2R","download_json":"https://pith.science/pith/6JKNKKOIIV3ECCDMKN234OPU2R.json","view_paper":"https://pith.science/paper/6JKNKKOI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.12180&json=true","fetch_graph":"https://pith.science/api/pith-number/6JKNKKOIIV3ECCDMKN234OPU2R/graph.json","fetch_events":"https://pith.science/api/pith-number/6JKNKKOIIV3ECCDMKN234OPU2R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6JKNKKOIIV3ECCDMKN234OPU2R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6JKNKKOIIV3ECCDMKN234OPU2R/action/storage_attestation","attest_author":"https://pith.science/pith/6JKNKKOIIV3ECCDMKN234OPU2R/action/author_attestation","sign_citation":"https://pith.science/pith/6JKNKKOIIV3ECCDMKN234OPU2R/action/citation_signature","submit_replication":"https://pith.science/pith/6JKNKKOIIV3ECCDMKN234OPU2R/action/replication_record"}},"created_at":"2026-07-05T08:35:33.078916+00:00","updated_at":"2026-07-05T08:35:33.078916+00:00"}