{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:BYE6OTAVVGOZFG2IRXMGNPG7XK","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":"7309fad360a3c3d9de027a005ad6ee6bc2d8401d5674b3d3a6a46972cc1e410b","cross_cats_sorted":["cs.HC","cs.RO","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-27T12:42:05Z","title_canon_sha256":"15416e72effea7cef47da4df5caa2887d831c3de4f987ccbdbcb7d24cf73baa8"},"schema_version":"1.0","source":{"id":"2109.13005","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.13005","created_at":"2026-07-05T03:17:40Z"},{"alias_kind":"arxiv_version","alias_value":"2109.13005v1","created_at":"2026-07-05T03:17:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.13005","created_at":"2026-07-05T03:17:40Z"},{"alias_kind":"pith_short_12","alias_value":"BYE6OTAVVGOZ","created_at":"2026-07-05T03:17:40Z"},{"alias_kind":"pith_short_16","alias_value":"BYE6OTAVVGOZFG2I","created_at":"2026-07-05T03:17:40Z"},{"alias_kind":"pith_short_8","alias_value":"BYE6OTAV","created_at":"2026-07-05T03:17:40Z"}],"graph_snapshots":[{"event_id":"sha256:b34baf259a6e4a6726906286153f245cda533ee7feb9113270d278570738cfe1","target":"graph","created_at":"2026-07-05T03:17:40Z","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/2109.13005/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In complex environments with high dimension, training a reinforcement learning (RL) model from scratch often suffers from lengthy and tedious collection of agent-environment interactions. Instead, leveraging expert demonstration to guide RL agent can boost sample efficiency and improve final convergence. In order to better integrate expert prior with on-policy RL models, we propose a generic framework for Learning from Demonstration (LfD) based on actor-critic algorithms. Technically, we first employ K-Means clustering to evaluate the similarity of sampled exploration with demonstration data. ","authors_text":"Binhao Chen, Chengliang Liu, Junping Zhang, Liang Gong, Shenghan Xie, Zhaorun Chen, Zhengfeng Zhang","cross_cats":["cs.HC","cs.RO","cs.SY","eess.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-27T12:42:05Z","title":"Efficiently Training On-Policy Actor-Critic Networks in Robotic Deep Reinforcement Learning with Demonstration-like Sampled Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.13005","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:f51bdb8d42f998a6644da15ec24a14b05917e6935d1d1667e5b7393652db6206","target":"record","created_at":"2026-07-05T03:17:40Z","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":"7309fad360a3c3d9de027a005ad6ee6bc2d8401d5674b3d3a6a46972cc1e410b","cross_cats_sorted":["cs.HC","cs.RO","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-27T12:42:05Z","title_canon_sha256":"15416e72effea7cef47da4df5caa2887d831c3de4f987ccbdbcb7d24cf73baa8"},"schema_version":"1.0","source":{"id":"2109.13005","kind":"arxiv","version":1}},"canonical_sha256":"0e09e74c15a99d929b488dd866bcdfbab652bac9d25e0a71a7fbe56ce18c1303","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e09e74c15a99d929b488dd866bcdfbab652bac9d25e0a71a7fbe56ce18c1303","first_computed_at":"2026-07-05T03:17:40.109624Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:17:40.109624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kvVUm98ybt4xqxuebPK01gkxi0+u11KWN5ljtO8E/ktpuF4Xx2aLoU085oA08WUtTAnu/2lVj+qDFQuONGEzDg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:17:40.110085Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.13005","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f51bdb8d42f998a6644da15ec24a14b05917e6935d1d1667e5b7393652db6206","sha256:b34baf259a6e4a6726906286153f245cda533ee7feb9113270d278570738cfe1"],"state_sha256":"2a2d0a6bd243480cedd563b1b020e1b8861651de313edd51b3863b3021600f4f"}