{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:DRGVX6EY7UVVSFVTAYKQUZYXX7","short_pith_number":"pith:DRGVX6EY","schema_version":"1.0","canonical_sha256":"1c4d5bf898fd2b5916b306150a6717bfc24a37bd670fd58c6ee6b240e7c035ed","source":{"kind":"arxiv","id":"2011.08027","version":1},"attestation_state":"computed","paper":{"title":"ACDER: Augmented Curiosity-Driven Experience Replay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Boyao Li, Jiayi Li, Ning Lu, Shuo Wang, Tao Lu, Yinghao Cai","submitted_at":"2020-11-16T15:27:15Z","abstract_excerpt":"Exploration in environments with sparse feedback remains a challenging research problem in reinforcement learning (RL). When the RL agent explores the environment randomly, it results in low exploration efficiency, especially in robotic manipulation tasks with high dimensional continuous state and action space. In this paper, we propose a novel method, called Augmented Curiosity-Driven Experience Replay (ACDER), which leverages (i) a new goal-oriented curiosity-driven exploration to encourage the agent to pursue novel and task-relevant states more purposefully and (ii) the dynamic initial stat"},"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":"2011.08027","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-16T15:27:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1ca40feb28ee50a4698377de22856342c3aa35f8da6598ccf5c460d8c83a99f5","abstract_canon_sha256":"0597d499bb1356c0c8d6c28f637657619eeb3bdb99da6332ea0350dc1dcb4c6f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:52:38.111767Z","signature_b64":"qDTZW1n684NsEx5X/shXXHCaVwSgwG0GzeJIJrNzc51UAY22kAuzSbyMD9vYEtFoaxJDk5nCquxeZV+1M6BMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c4d5bf898fd2b5916b306150a6717bfc24a37bd670fd58c6ee6b240e7c035ed","last_reissued_at":"2026-07-05T01:52:38.111357Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:52:38.111357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ACDER: Augmented Curiosity-Driven Experience Replay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Boyao Li, Jiayi Li, Ning Lu, Shuo Wang, Tao Lu, Yinghao Cai","submitted_at":"2020-11-16T15:27:15Z","abstract_excerpt":"Exploration in environments with sparse feedback remains a challenging research problem in reinforcement learning (RL). When the RL agent explores the environment randomly, it results in low exploration efficiency, especially in robotic manipulation tasks with high dimensional continuous state and action space. In this paper, we propose a novel method, called Augmented Curiosity-Driven Experience Replay (ACDER), which leverages (i) a new goal-oriented curiosity-driven exploration to encourage the agent to pursue novel and task-relevant states more purposefully and (ii) the dynamic initial stat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.08027","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2011.08027/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":"2011.08027","created_at":"2026-07-05T01:52:38.111415+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.08027v1","created_at":"2026-07-05T01:52:38.111415+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.08027","created_at":"2026-07-05T01:52:38.111415+00:00"},{"alias_kind":"pith_short_12","alias_value":"DRGVX6EY7UVV","created_at":"2026-07-05T01:52:38.111415+00:00"},{"alias_kind":"pith_short_16","alias_value":"DRGVX6EY7UVVSFVT","created_at":"2026-07-05T01:52:38.111415+00:00"},{"alias_kind":"pith_short_8","alias_value":"DRGVX6EY","created_at":"2026-07-05T01:52:38.111415+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/DRGVX6EY7UVVSFVTAYKQUZYXX7","json":"https://pith.science/pith/DRGVX6EY7UVVSFVTAYKQUZYXX7.json","graph_json":"https://pith.science/api/pith-number/DRGVX6EY7UVVSFVTAYKQUZYXX7/graph.json","events_json":"https://pith.science/api/pith-number/DRGVX6EY7UVVSFVTAYKQUZYXX7/events.json","paper":"https://pith.science/paper/DRGVX6EY"},"agent_actions":{"view_html":"https://pith.science/pith/DRGVX6EY7UVVSFVTAYKQUZYXX7","download_json":"https://pith.science/pith/DRGVX6EY7UVVSFVTAYKQUZYXX7.json","view_paper":"https://pith.science/paper/DRGVX6EY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.08027&json=true","fetch_graph":"https://pith.science/api/pith-number/DRGVX6EY7UVVSFVTAYKQUZYXX7/graph.json","fetch_events":"https://pith.science/api/pith-number/DRGVX6EY7UVVSFVTAYKQUZYXX7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DRGVX6EY7UVVSFVTAYKQUZYXX7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DRGVX6EY7UVVSFVTAYKQUZYXX7/action/storage_attestation","attest_author":"https://pith.science/pith/DRGVX6EY7UVVSFVTAYKQUZYXX7/action/author_attestation","sign_citation":"https://pith.science/pith/DRGVX6EY7UVVSFVTAYKQUZYXX7/action/citation_signature","submit_replication":"https://pith.science/pith/DRGVX6EY7UVVSFVTAYKQUZYXX7/action/replication_record"}},"created_at":"2026-07-05T01:52:38.111415+00:00","updated_at":"2026-07-05T01:52:38.111415+00:00"}