{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BGJMPR7EU2NGYMK77SD4NZLYSU","short_pith_number":"pith:BGJMPR7E","schema_version":"1.0","canonical_sha256":"0992c7c7e4a69a6c315ffc87c6e578950c0808f6685347221925a884c57d9679","source":{"kind":"arxiv","id":"2106.01016","version":2},"attestation_state":"computed","paper":{"title":"Deep Reinforcement Learning-based UAV Navigation and Control: A Soft Actor-Critic with Hindsight Experience Replay Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO","cs.SY"],"primary_cat":"eess.SY","authors_text":"Jun Moon, Myoung Hoon Lee","submitted_at":"2021-06-02T08:30:14Z","abstract_excerpt":"In this paper, we propose SACHER (soft actor-critic (SAC) with hindsight experience replay (HER)), which constitutes a class of deep reinforcement learning (DRL) algorithms. SAC is known as an off-policy model-free DRL algorithm based on the maximum entropy framework, which outperforms earlier DRL algorithms in terms of exploration, robustness and learning performance. However, in SAC, maximizing the entropy-augmented objective may degrade the optimality of learning outcomes. HER is known as a sample-efficient replay method that enhances the performance of off-policy DRL algorithms by allowing"},"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":"2106.01016","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2021-06-02T08:30:14Z","cross_cats_sorted":["cs.LG","cs.RO","cs.SY"],"title_canon_sha256":"06f7229626c157e7e75e15a38568fe3ed342d295647f9b76bae493599aa3f57f","abstract_canon_sha256":"0724a04f4e138ed47210827e9fd825cc6f95651c0f06fcf27c62fb22db18011b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:28.589141Z","signature_b64":"TElCGwfffs+9JkQWHBfdkD4pWQFBescWvEwPErdAMi5Hp27Amp1tXRKzQEabRMnKmbAxH1QFfa5G7BK18hrgDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0992c7c7e4a69a6c315ffc87c6e578950c0808f6685347221925a884c57d9679","last_reissued_at":"2026-07-05T02:46:28.588721Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:28.588721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning-based UAV Navigation and Control: A Soft Actor-Critic with Hindsight Experience Replay Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO","cs.SY"],"primary_cat":"eess.SY","authors_text":"Jun Moon, Myoung Hoon Lee","submitted_at":"2021-06-02T08:30:14Z","abstract_excerpt":"In this paper, we propose SACHER (soft actor-critic (SAC) with hindsight experience replay (HER)), which constitutes a class of deep reinforcement learning (DRL) algorithms. SAC is known as an off-policy model-free DRL algorithm based on the maximum entropy framework, which outperforms earlier DRL algorithms in terms of exploration, robustness and learning performance. However, in SAC, maximizing the entropy-augmented objective may degrade the optimality of learning outcomes. HER is known as a sample-efficient replay method that enhances the performance of off-policy DRL algorithms by allowing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.01016","kind":"arxiv","version":2},"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/2106.01016/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":"2106.01016","created_at":"2026-07-05T02:46:28.588772+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.01016v2","created_at":"2026-07-05T02:46:28.588772+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.01016","created_at":"2026-07-05T02:46:28.588772+00:00"},{"alias_kind":"pith_short_12","alias_value":"BGJMPR7EU2NG","created_at":"2026-07-05T02:46:28.588772+00:00"},{"alias_kind":"pith_short_16","alias_value":"BGJMPR7EU2NGYMK7","created_at":"2026-07-05T02:46:28.588772+00:00"},{"alias_kind":"pith_short_8","alias_value":"BGJMPR7E","created_at":"2026-07-05T02:46:28.588772+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.05615","citing_title":"When Maximum Entropy Misleads Policy Optimization","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BGJMPR7EU2NGYMK77SD4NZLYSU","json":"https://pith.science/pith/BGJMPR7EU2NGYMK77SD4NZLYSU.json","graph_json":"https://pith.science/api/pith-number/BGJMPR7EU2NGYMK77SD4NZLYSU/graph.json","events_json":"https://pith.science/api/pith-number/BGJMPR7EU2NGYMK77SD4NZLYSU/events.json","paper":"https://pith.science/paper/BGJMPR7E"},"agent_actions":{"view_html":"https://pith.science/pith/BGJMPR7EU2NGYMK77SD4NZLYSU","download_json":"https://pith.science/pith/BGJMPR7EU2NGYMK77SD4NZLYSU.json","view_paper":"https://pith.science/paper/BGJMPR7E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.01016&json=true","fetch_graph":"https://pith.science/api/pith-number/BGJMPR7EU2NGYMK77SD4NZLYSU/graph.json","fetch_events":"https://pith.science/api/pith-number/BGJMPR7EU2NGYMK77SD4NZLYSU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BGJMPR7EU2NGYMK77SD4NZLYSU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BGJMPR7EU2NGYMK77SD4NZLYSU/action/storage_attestation","attest_author":"https://pith.science/pith/BGJMPR7EU2NGYMK77SD4NZLYSU/action/author_attestation","sign_citation":"https://pith.science/pith/BGJMPR7EU2NGYMK77SD4NZLYSU/action/citation_signature","submit_replication":"https://pith.science/pith/BGJMPR7EU2NGYMK77SD4NZLYSU/action/replication_record"}},"created_at":"2026-07-05T02:46:28.588772+00:00","updated_at":"2026-07-05T02:46:28.588772+00:00"}