{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BYE6OTAVVGOZFG2IRXMGNPG7XK","short_pith_number":"pith:BYE6OTAV","schema_version":"1.0","canonical_sha256":"0e09e74c15a99d929b488dd866bcdfbab652bac9d25e0a71a7fbe56ce18c1303","source":{"kind":"arxiv","id":"2109.13005","version":1},"attestation_state":"computed","paper":{"title":"Efficiently Training On-Policy Actor-Critic Networks in Robotic Deep Reinforcement Learning with Demonstration-like Sampled Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.RO","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Binhao Chen, Chengliang Liu, Junping Zhang, Liang Gong, Shenghan Xie, Zhaorun Chen, Zhengfeng Zhang","submitted_at":"2021-09-27T12:42:05Z","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. "},"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":"2109.13005","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-27T12:42:05Z","cross_cats_sorted":["cs.HC","cs.RO","cs.SY","eess.SY"],"title_canon_sha256":"15416e72effea7cef47da4df5caa2887d831c3de4f987ccbdbcb7d24cf73baa8","abstract_canon_sha256":"7309fad360a3c3d9de027a005ad6ee6bc2d8401d5674b3d3a6a46972cc1e410b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:17:40.110085Z","signature_b64":"kvVUm98ybt4xqxuebPK01gkxi0+u11KWN5ljtO8E/ktpuF4Xx2aLoU085oA08WUtTAnu/2lVj+qDFQuONGEzDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e09e74c15a99d929b488dd866bcdfbab652bac9d25e0a71a7fbe56ce18c1303","last_reissued_at":"2026-07-05T03:17:40.109624Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:17:40.109624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficiently Training On-Policy Actor-Critic Networks in Robotic Deep Reinforcement Learning with Demonstration-like Sampled Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.RO","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Binhao Chen, Chengliang Liu, Junping Zhang, Liang Gong, Shenghan Xie, Zhaorun Chen, Zhengfeng Zhang","submitted_at":"2021-09-27T12:42:05Z","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. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.13005","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2109.13005/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2109.13005","created_at":"2026-07-05T03:17:40.109680+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.13005v1","created_at":"2026-07-05T03:17:40.109680+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.13005","created_at":"2026-07-05T03:17:40.109680+00:00"},{"alias_kind":"pith_short_12","alias_value":"BYE6OTAVVGOZ","created_at":"2026-07-05T03:17:40.109680+00:00"},{"alias_kind":"pith_short_16","alias_value":"BYE6OTAVVGOZFG2I","created_at":"2026-07-05T03:17:40.109680+00:00"},{"alias_kind":"pith_short_8","alias_value":"BYE6OTAV","created_at":"2026-07-05T03:17:40.109680+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/BYE6OTAVVGOZFG2IRXMGNPG7XK","json":"https://pith.science/pith/BYE6OTAVVGOZFG2IRXMGNPG7XK.json","graph_json":"https://pith.science/api/pith-number/BYE6OTAVVGOZFG2IRXMGNPG7XK/graph.json","events_json":"https://pith.science/api/pith-number/BYE6OTAVVGOZFG2IRXMGNPG7XK/events.json","paper":"https://pith.science/paper/BYE6OTAV"},"agent_actions":{"view_html":"https://pith.science/pith/BYE6OTAVVGOZFG2IRXMGNPG7XK","download_json":"https://pith.science/pith/BYE6OTAVVGOZFG2IRXMGNPG7XK.json","view_paper":"https://pith.science/paper/BYE6OTAV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.13005&json=true","fetch_graph":"https://pith.science/api/pith-number/BYE6OTAVVGOZFG2IRXMGNPG7XK/graph.json","fetch_events":"https://pith.science/api/pith-number/BYE6OTAVVGOZFG2IRXMGNPG7XK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BYE6OTAVVGOZFG2IRXMGNPG7XK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BYE6OTAVVGOZFG2IRXMGNPG7XK/action/storage_attestation","attest_author":"https://pith.science/pith/BYE6OTAVVGOZFG2IRXMGNPG7XK/action/author_attestation","sign_citation":"https://pith.science/pith/BYE6OTAVVGOZFG2IRXMGNPG7XK/action/citation_signature","submit_replication":"https://pith.science/pith/BYE6OTAVVGOZFG2IRXMGNPG7XK/action/replication_record"}},"created_at":"2026-07-05T03:17:40.109680+00:00","updated_at":"2026-07-05T03:17:40.109680+00:00"}