{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:DRGVX6EY7UVVSFVTAYKQUZYXX7","short_pith_number":"pith:DRGVX6EY","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"},"canonical_sha256":"1c4d5bf898fd2b5916b306150a6717bfc24a37bd670fd58c6ee6b240e7c035ed","source":{"kind":"arxiv","id":"2011.08027","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.08027","created_at":"2026-07-05T01:52:38Z"},{"alias_kind":"arxiv_version","alias_value":"2011.08027v1","created_at":"2026-07-05T01:52:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.08027","created_at":"2026-07-05T01:52:38Z"},{"alias_kind":"pith_short_12","alias_value":"DRGVX6EY7UVV","created_at":"2026-07-05T01:52:38Z"},{"alias_kind":"pith_short_16","alias_value":"DRGVX6EY7UVVSFVT","created_at":"2026-07-05T01:52:38Z"},{"alias_kind":"pith_short_8","alias_value":"DRGVX6EY","created_at":"2026-07-05T01:52:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:DRGVX6EY7UVVSFVTAYKQUZYXX7","target":"record","payload":{"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"},"canonical_sha256":"1c4d5bf898fd2b5916b306150a6717bfc24a37bd670fd58c6ee6b240e7c035ed","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"},"source_kind":"arxiv","source_id":"2011.08027","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":"2026-07-05T01:52:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"apt3xaXEdGhNy2k/inX109aBb+1cl5zC2ykIPvysIOGCfDWtpFtDK4uPAusTL3Pcp+4MNbiprnGH53Jle5p6BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:24:21.582445Z"},"content_sha256":"76819e315ef47bd18775e6049883b68943d6667f23b79d40d657d9d980609788","schema_version":"1.0","event_id":"sha256:76819e315ef47bd18775e6049883b68943d6667f23b79d40d657d9d980609788"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:DRGVX6EY7UVVSFVTAYKQUZYXX7","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:52:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lU94Uh/w6stpy7/tZ/yQk67mDFPoeElSreu2t2IeXsV1V2P/H5B0aKJunrlk0hqrJwIBcWDEqZfU5zTdYNTbBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:24:21.582982Z"},"content_sha256":"f1300cb4be0aeb5633b4a6b2a48509b556632236aa3d4c6c0699fe0a47c1cc75","schema_version":"1.0","event_id":"sha256:f1300cb4be0aeb5633b4a6b2a48509b556632236aa3d4c6c0699fe0a47c1cc75"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DRGVX6EY7UVVSFVTAYKQUZYXX7/bundle.json","state_url":"https://pith.science/pith/DRGVX6EY7UVVSFVTAYKQUZYXX7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DRGVX6EY7UVVSFVTAYKQUZYXX7/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":"2026-08-04T05:24:21Z","links":{"resolver":"https://pith.science/pith/DRGVX6EY7UVVSFVTAYKQUZYXX7","bundle":"https://pith.science/pith/DRGVX6EY7UVVSFVTAYKQUZYXX7/bundle.json","state":"https://pith.science/pith/DRGVX6EY7UVVSFVTAYKQUZYXX7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DRGVX6EY7UVVSFVTAYKQUZYXX7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:DRGVX6EY7UVVSFVTAYKQUZYXX7","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":"0597d499bb1356c0c8d6c28f637657619eeb3bdb99da6332ea0350dc1dcb4c6f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-16T15:27:15Z","title_canon_sha256":"1ca40feb28ee50a4698377de22856342c3aa35f8da6598ccf5c460d8c83a99f5"},"schema_version":"1.0","source":{"id":"2011.08027","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.08027","created_at":"2026-07-05T01:52:38Z"},{"alias_kind":"arxiv_version","alias_value":"2011.08027v1","created_at":"2026-07-05T01:52:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.08027","created_at":"2026-07-05T01:52:38Z"},{"alias_kind":"pith_short_12","alias_value":"DRGVX6EY7UVV","created_at":"2026-07-05T01:52:38Z"},{"alias_kind":"pith_short_16","alias_value":"DRGVX6EY7UVVSFVT","created_at":"2026-07-05T01:52:38Z"},{"alias_kind":"pith_short_8","alias_value":"DRGVX6EY","created_at":"2026-07-05T01:52:38Z"}],"graph_snapshots":[{"event_id":"sha256:f1300cb4be0aeb5633b4a6b2a48509b556632236aa3d4c6c0699fe0a47c1cc75","target":"graph","created_at":"2026-07-05T01:52:38Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2011.08027/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Boyao Li, Jiayi Li, Ning Lu, Shuo Wang, Tao Lu, Yinghao Cai","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-16T15:27:15Z","title":"ACDER: Augmented Curiosity-Driven Experience Replay"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.08027","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":"sha256:76819e315ef47bd18775e6049883b68943d6667f23b79d40d657d9d980609788","target":"record","created_at":"2026-07-05T01:52:38Z","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":"0597d499bb1356c0c8d6c28f637657619eeb3bdb99da6332ea0350dc1dcb4c6f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-16T15:27:15Z","title_canon_sha256":"1ca40feb28ee50a4698377de22856342c3aa35f8da6598ccf5c460d8c83a99f5"},"schema_version":"1.0","source":{"id":"2011.08027","kind":"arxiv","version":1}},"canonical_sha256":"1c4d5bf898fd2b5916b306150a6717bfc24a37bd670fd58c6ee6b240e7c035ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c4d5bf898fd2b5916b306150a6717bfc24a37bd670fd58c6ee6b240e7c035ed","first_computed_at":"2026-07-05T01:52:38.111357Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:52:38.111357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qDTZW1n684NsEx5X/shXXHCaVwSgwG0GzeJIJrNzc51UAY22kAuzSbyMD9vYEtFoaxJDk5nCquxeZV+1M6BMCw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:52:38.111767Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.08027","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76819e315ef47bd18775e6049883b68943d6667f23b79d40d657d9d980609788","sha256:f1300cb4be0aeb5633b4a6b2a48509b556632236aa3d4c6c0699fe0a47c1cc75"],"state_sha256":"399e69abfd4d4a9e94000ab7b664ae34967868ac8a1ed42b249b173acea2f35d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XriNYb1ZWAh28vXZTfAcm/1fYhAYb89sVmH9xfGX+JASmD2ppCYDITvWPg1wTM6PW2cRG6B7MWwm2bO4j0yABg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T05:24:21.590454Z","bundle_sha256":"1aace8544a03ac62d94d29fbf081d74d264b2a2a3bac06c2dbd8c0306bab17bf"}}