{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:BI7TUMVXCNJO4ATDBDYYQTSWY3","short_pith_number":"pith:BI7TUMVX","schema_version":"1.0","canonical_sha256":"0a3f3a32b71352ee026308f1884e56c6c2560ec587c92e0fa8cb19fee26f1d8a","source":{"kind":"arxiv","id":"1906.03710","version":1},"attestation_state":"computed","paper":{"title":"Curiosity-Driven Multi-Criteria Hindsight Experience Replay","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"John B. Lanier, Pierre Baldi, Stephen McAleer","submitted_at":"2019-06-09T21:11:08Z","abstract_excerpt":"Dealing with sparse rewards is a longstanding challenge in reinforcement learning. The recent use of hindsight methods have achieved success on a variety of sparse-reward tasks, but they fail on complex tasks such as stacking multiple blocks with a robot arm in simulation. Curiosity-driven exploration using the prediction error of a learned dynamics model as an intrinsic reward has been shown to be effective for exploring a number of sparse-reward environments. We present a method that combines hindsight with curiosity-driven exploration and curriculum learning in order to solve the challengin"},"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":"1906.03710","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-06-09T21:11:08Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"cb1719ef5ac46663c5ccb425921f608b9cf0797195d9551b4aba5595f37fd848","abstract_canon_sha256":"6372c5ec2b9411e215b335cf5cf415e1f53455c4c02c9740039f2e7e9980e9c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:45.244545Z","signature_b64":"2peWSchV0PVklOSzce3P2Hti5gGdQ/6f3z0BImeUCZr4TykTHJJPKl9C9hcEc7zH9oNztA9JnxP7bPfPRu4fCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a3f3a32b71352ee026308f1884e56c6c2560ec587c92e0fa8cb19fee26f1d8a","last_reissued_at":"2026-05-17T23:43:45.243848Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:45.243848Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Curiosity-Driven Multi-Criteria Hindsight Experience Replay","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"John B. Lanier, Pierre Baldi, Stephen McAleer","submitted_at":"2019-06-09T21:11:08Z","abstract_excerpt":"Dealing with sparse rewards is a longstanding challenge in reinforcement learning. The recent use of hindsight methods have achieved success on a variety of sparse-reward tasks, but they fail on complex tasks such as stacking multiple blocks with a robot arm in simulation. Curiosity-driven exploration using the prediction error of a learned dynamics model as an intrinsic reward has been shown to be effective for exploring a number of sparse-reward environments. We present a method that combines hindsight with curiosity-driven exploration and curriculum learning in order to solve the challengin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03710","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":"1906.03710","created_at":"2026-05-17T23:43:45.243953+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.03710v1","created_at":"2026-05-17T23:43:45.243953+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03710","created_at":"2026-05-17T23:43:45.243953+00:00"},{"alias_kind":"pith_short_12","alias_value":"BI7TUMVXCNJO","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"BI7TUMVXCNJO4ATD","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"BI7TUMVX","created_at":"2026-05-18T12:33:12.712433+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/BI7TUMVXCNJO4ATDBDYYQTSWY3","json":"https://pith.science/pith/BI7TUMVXCNJO4ATDBDYYQTSWY3.json","graph_json":"https://pith.science/api/pith-number/BI7TUMVXCNJO4ATDBDYYQTSWY3/graph.json","events_json":"https://pith.science/api/pith-number/BI7TUMVXCNJO4ATDBDYYQTSWY3/events.json","paper":"https://pith.science/paper/BI7TUMVX"},"agent_actions":{"view_html":"https://pith.science/pith/BI7TUMVXCNJO4ATDBDYYQTSWY3","download_json":"https://pith.science/pith/BI7TUMVXCNJO4ATDBDYYQTSWY3.json","view_paper":"https://pith.science/paper/BI7TUMVX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.03710&json=true","fetch_graph":"https://pith.science/api/pith-number/BI7TUMVXCNJO4ATDBDYYQTSWY3/graph.json","fetch_events":"https://pith.science/api/pith-number/BI7TUMVXCNJO4ATDBDYYQTSWY3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BI7TUMVXCNJO4ATDBDYYQTSWY3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BI7TUMVXCNJO4ATDBDYYQTSWY3/action/storage_attestation","attest_author":"https://pith.science/pith/BI7TUMVXCNJO4ATDBDYYQTSWY3/action/author_attestation","sign_citation":"https://pith.science/pith/BI7TUMVXCNJO4ATDBDYYQTSWY3/action/citation_signature","submit_replication":"https://pith.science/pith/BI7TUMVXCNJO4ATDBDYYQTSWY3/action/replication_record"}},"created_at":"2026-05-17T23:43:45.243953+00:00","updated_at":"2026-05-17T23:43:45.243953+00:00"}