{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:KQRN33ZCQGGKLFAGKT37YRLT6G","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":"d4b5de550fc95f70e4d6f1eb0d7362169ba6a858a56751a38ebfb88300b60efb","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-09-17T16:52:03Z","title_canon_sha256":"0b5918833efba9812b84812c4abfd19e95caec791d74733e988012fdb668f5d4"},"schema_version":"1.0","source":{"id":"2109.08642","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.08642","created_at":"2026-07-05T07:21:59Z"},{"alias_kind":"arxiv_version","alias_value":"2109.08642v2","created_at":"2026-07-05T07:21:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.08642","created_at":"2026-07-05T07:21:59Z"},{"alias_kind":"pith_short_12","alias_value":"KQRN33ZCQGGK","created_at":"2026-07-05T07:21:59Z"},{"alias_kind":"pith_short_16","alias_value":"KQRN33ZCQGGKLFAG","created_at":"2026-07-05T07:21:59Z"},{"alias_kind":"pith_short_8","alias_value":"KQRN33ZC","created_at":"2026-07-05T07:21:59Z"}],"graph_snapshots":[{"event_id":"sha256:1f7dbf34be2f72a6cdaae14ad9aa539a2fb8a47cd70c15c987e769755df8a1be","target":"graph","created_at":"2026-07-05T07:21:59Z","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/2109.08642/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While the rapid progress of deep learning fuels end-to-end reinforcement learning (RL), direct application, especially in high-dimensional space like robotic scenarios still suffers from low sample efficiency. Therefore State Representation Learning (SRL) is proposed to specifically learn to encode task-relevant features from complex sensory data into low-dimensional states. However, the pervasive implementation of SRL is usually conducted by a decoupling strategy in which the observation-state mapping is learned separately, which is prone to over-fit. To handle such problem, we summarize the ","authors_text":"Binhao Chen, Chengliang Liu, David Filliat, Liang Gong, Natalia D\\'iaz-Rodr\\'iguez, Siqi Fan, Te Sun, Yuan Tan, Zhaorun Chen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-09-17T16:52:03Z","title":"POAR: Efficient Policy Optimization via Online Abstract State Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.08642","kind":"arxiv","version":2},"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":"sha256:9a48e0fb6bcb63121a8adb24275a68b4ad83b6c275fae40944ad4d5903de1ccc","target":"record","created_at":"2026-07-05T07:21:59Z","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":"d4b5de550fc95f70e4d6f1eb0d7362169ba6a858a56751a38ebfb88300b60efb","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-09-17T16:52:03Z","title_canon_sha256":"0b5918833efba9812b84812c4abfd19e95caec791d74733e988012fdb668f5d4"},"schema_version":"1.0","source":{"id":"2109.08642","kind":"arxiv","version":2}},"canonical_sha256":"5422ddef22818ca5940654f7fc4573f1a8a6e1a4f5e678db9cd3610079b32c2e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5422ddef22818ca5940654f7fc4573f1a8a6e1a4f5e678db9cd3610079b32c2e","first_computed_at":"2026-07-05T07:21:59.356665Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:21:59.356665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5MsdNwURXpGy+YpO6f6adUGjjR2wYWlO9SWVviXd3AnUzm52wqKsas5nOEeoICT/ydx3Qg+brCMfIGC7TCGIBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:21:59.357112Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.08642","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a48e0fb6bcb63121a8adb24275a68b4ad83b6c275fae40944ad4d5903de1ccc","sha256:1f7dbf34be2f72a6cdaae14ad9aa539a2fb8a47cd70c15c987e769755df8a1be"],"state_sha256":"b23e702bdf48c7df996dfebbda21ec2382f5623d36539a45f959de462527f2cf"}