{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:BI7TUMVXCNJO4ATDBDYYQTSWY3","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":"6372c5ec2b9411e215b335cf5cf415e1f53455c4c02c9740039f2e7e9980e9c0","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-06-09T21:11:08Z","title_canon_sha256":"cb1719ef5ac46663c5ccb425921f608b9cf0797195d9551b4aba5595f37fd848"},"schema_version":"1.0","source":{"id":"1906.03710","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.03710","created_at":"2026-05-17T23:43:45Z"},{"alias_kind":"arxiv_version","alias_value":"1906.03710v1","created_at":"2026-05-17T23:43:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03710","created_at":"2026-05-17T23:43:45Z"},{"alias_kind":"pith_short_12","alias_value":"BI7TUMVXCNJO","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"BI7TUMVXCNJO4ATD","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"BI7TUMVX","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:b61c0ff1da56bd9d208e474da0de77983c5fc97587f3d33e319ce11116d0be59","target":"graph","created_at":"2026-05-17T23:43:45Z","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"},"paper":{"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","authors_text":"John B. Lanier, Pierre Baldi, Stephen McAleer","cross_cats":["cs.AI","cs.RO","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-06-09T21:11:08Z","title":"Curiosity-Driven Multi-Criteria Hindsight Experience Replay"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03710","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:a2a7e2445d30a5a32932e248aa9546620ca02bcc0e362cc6b56a4d1f99646f21","target":"record","created_at":"2026-05-17T23:43:45Z","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":"6372c5ec2b9411e215b335cf5cf415e1f53455c4c02c9740039f2e7e9980e9c0","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-06-09T21:11:08Z","title_canon_sha256":"cb1719ef5ac46663c5ccb425921f608b9cf0797195d9551b4aba5595f37fd848"},"schema_version":"1.0","source":{"id":"1906.03710","kind":"arxiv","version":1}},"canonical_sha256":"0a3f3a32b71352ee026308f1884e56c6c2560ec587c92e0fa8cb19fee26f1d8a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a3f3a32b71352ee026308f1884e56c6c2560ec587c92e0fa8cb19fee26f1d8a","first_computed_at":"2026-05-17T23:43:45.243848Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:45.243848Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2peWSchV0PVklOSzce3P2Hti5gGdQ/6f3z0BImeUCZr4TykTHJJPKl9C9hcEc7zH9oNztA9JnxP7bPfPRu4fCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:45.244545Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.03710","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a2a7e2445d30a5a32932e248aa9546620ca02bcc0e362cc6b56a4d1f99646f21","sha256:b61c0ff1da56bd9d208e474da0de77983c5fc97587f3d33e319ce11116d0be59"],"state_sha256":"586098dabd88996ac3b14467712c46793c7c66f66b4abd76d59c862730a2cddf"}