{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:QXWIRMY4UQEXUUR6PBZMBVGXFY","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":"b299d028cfab0a268b9600e9eb1761ac8d4c865b3e5dbbe4801f50a30194c84b","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-10-16T01:43:51Z","title_canon_sha256":"5dfb43c7aab2c1ed0b93426dd8a6da94b3507010c1811fc41bfa6bbd0803d9df"},"schema_version":"1.0","source":{"id":"1810.06784","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.06784","created_at":"2026-07-05T03:55:59Z"},{"alias_kind":"arxiv_version","alias_value":"1810.06784v4","created_at":"2026-07-05T03:55:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.06784","created_at":"2026-07-05T03:55:59Z"},{"alias_kind":"pith_short_12","alias_value":"QXWIRMY4UQEX","created_at":"2026-07-05T03:55:59Z"},{"alias_kind":"pith_short_16","alias_value":"QXWIRMY4UQEXUUR6","created_at":"2026-07-05T03:55:59Z"},{"alias_kind":"pith_short_8","alias_value":"QXWIRMY4","created_at":"2026-07-05T03:55:59Z"}],"graph_snapshots":[{"event_id":"sha256:94b73dc5f40f1f7e2ada67a0ad7ae544a4ab20b6dbcc4a593d4c667011cd3778","target":"graph","created_at":"2026-07-05T03:55:59Z","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/1810.06784/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Credit assignment in Meta-reinforcement learning (Meta-RL) is still poorly understood. Existing methods either neglect credit assignment to pre-adaptation behavior or implement it naively. This leads to poor sample-efficiency during meta-training as well as ineffective task identification strategies. This paper provides a theoretical analysis of credit assignment in gradient-based Meta-RL. Building on the gained insights we develop a novel meta-learning algorithm that overcomes both the issue of poor credit assignment and previous difficulties in estimating meta-policy gradients. By controllin","authors_text":"Dennis Lee, Ignasi Clavera, Jonas Rothfuss, Pieter Abbeel, Tamim Asfour","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-10-16T01:43:51Z","title":"ProMP: Proximal Meta-Policy Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.06784","kind":"arxiv","version":4},"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:f8391c328ce73eeb459bd1a8dfd962c150b666af19eb751b31ef35d48a3f1e02","target":"record","created_at":"2026-07-05T03:55:59Z","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":"b299d028cfab0a268b9600e9eb1761ac8d4c865b3e5dbbe4801f50a30194c84b","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-10-16T01:43:51Z","title_canon_sha256":"5dfb43c7aab2c1ed0b93426dd8a6da94b3507010c1811fc41bfa6bbd0803d9df"},"schema_version":"1.0","source":{"id":"1810.06784","kind":"arxiv","version":4}},"canonical_sha256":"85ec88b31ca4097a523e7872c0d4d72e21f08ff8df7d656c92e9f2d70a287385","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85ec88b31ca4097a523e7872c0d4d72e21f08ff8df7d656c92e9f2d70a287385","first_computed_at":"2026-07-05T03:55:59.341225Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:55:59.341225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XEekzmbj2jyhJlkhwKFaqKjHxVQTBWSxB+f+gIR8el5B7p7+tCUddQuZaP2tykAtF2/OxKIQPtzx+tKB66g7CA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:55:59.341744Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.06784","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8391c328ce73eeb459bd1a8dfd962c150b666af19eb751b31ef35d48a3f1e02","sha256:94b73dc5f40f1f7e2ada67a0ad7ae544a4ab20b6dbcc4a593d4c667011cd3778"],"state_sha256":"e24d5831ae160585f45ee1156cb6584d7b1d14e5acc8438f0486e13c443ababf"}