{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BKBTX3GWJZRILLGHRHLFODW2MM","short_pith_number":"pith:BKBTX3GW","schema_version":"1.0","canonical_sha256":"0a833becd64e6285acc789d6570eda63037e833cfab2dcccc8cc758ab83f455e","source":{"kind":"arxiv","id":"2312.16189","version":1},"attestation_state":"computed","paper":{"title":"OpenRL: A Unified Reinforcement Learning Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fuqing Bie, Shiyu Huang, Wei-Wei Tu, Wentse Chen, Yiwen Sun","submitted_at":"2023-12-20T12:04:06Z","abstract_excerpt":"We present OpenRL, an advanced reinforcement learning (RL) framework designed to accommodate a diverse array of tasks, from single-agent challenges to complex multi-agent systems. OpenRL's robust support for self-play training empowers agents to develop advanced strategies in competitive settings. Notably, OpenRL integrates Natural Language Processing (NLP) with RL, enabling researchers to address a combination of RL training and language-centric tasks effectively. Leveraging PyTorch's robust capabilities, OpenRL exemplifies modularity and a user-centric approach. It offers a universal interfa"},"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":"2312.16189","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-20T12:04:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"224e80979d2091fde40dfb8cfc2fe59c0af75cfcf532b9825843882edd535c98","abstract_canon_sha256":"9c1d8e8515218ad479b8862ba184c7234658e660499476fba371e0bb16d10a3a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:13.960620Z","signature_b64":"SPl5FoihYFEx1xXCDGYNzKEeJjw5schUdAYGlXse1gOjJkBmX5YPnhK84ORUUqfFOVjVe35G/L8e9mtVvKT2DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a833becd64e6285acc789d6570eda63037e833cfab2dcccc8cc758ab83f455e","last_reissued_at":"2026-07-05T07:28:13.960218Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:13.960218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenRL: A Unified Reinforcement Learning Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fuqing Bie, Shiyu Huang, Wei-Wei Tu, Wentse Chen, Yiwen Sun","submitted_at":"2023-12-20T12:04:06Z","abstract_excerpt":"We present OpenRL, an advanced reinforcement learning (RL) framework designed to accommodate a diverse array of tasks, from single-agent challenges to complex multi-agent systems. OpenRL's robust support for self-play training empowers agents to develop advanced strategies in competitive settings. Notably, OpenRL integrates Natural Language Processing (NLP) with RL, enabling researchers to address a combination of RL training and language-centric tasks effectively. Leveraging PyTorch's robust capabilities, OpenRL exemplifies modularity and a user-centric approach. It offers a universal interfa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.16189","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/2312.16189/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":"2312.16189","created_at":"2026-07-05T07:28:13.960273+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.16189v1","created_at":"2026-07-05T07:28:13.960273+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.16189","created_at":"2026-07-05T07:28:13.960273+00:00"},{"alias_kind":"pith_short_12","alias_value":"BKBTX3GWJZRI","created_at":"2026-07-05T07:28:13.960273+00:00"},{"alias_kind":"pith_short_16","alias_value":"BKBTX3GWJZRILLGH","created_at":"2026-07-05T07:28:13.960273+00:00"},{"alias_kind":"pith_short_8","alias_value":"BKBTX3GW","created_at":"2026-07-05T07:28:13.960273+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.14380","citing_title":"CRAFT: Coaching Reinforcement Learning Autonomously using Foundation Models for Multi-Robot Coordination Tasks","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BKBTX3GWJZRILLGHRHLFODW2MM","json":"https://pith.science/pith/BKBTX3GWJZRILLGHRHLFODW2MM.json","graph_json":"https://pith.science/api/pith-number/BKBTX3GWJZRILLGHRHLFODW2MM/graph.json","events_json":"https://pith.science/api/pith-number/BKBTX3GWJZRILLGHRHLFODW2MM/events.json","paper":"https://pith.science/paper/BKBTX3GW"},"agent_actions":{"view_html":"https://pith.science/pith/BKBTX3GWJZRILLGHRHLFODW2MM","download_json":"https://pith.science/pith/BKBTX3GWJZRILLGHRHLFODW2MM.json","view_paper":"https://pith.science/paper/BKBTX3GW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.16189&json=true","fetch_graph":"https://pith.science/api/pith-number/BKBTX3GWJZRILLGHRHLFODW2MM/graph.json","fetch_events":"https://pith.science/api/pith-number/BKBTX3GWJZRILLGHRHLFODW2MM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BKBTX3GWJZRILLGHRHLFODW2MM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BKBTX3GWJZRILLGHRHLFODW2MM/action/storage_attestation","attest_author":"https://pith.science/pith/BKBTX3GWJZRILLGHRHLFODW2MM/action/author_attestation","sign_citation":"https://pith.science/pith/BKBTX3GWJZRILLGHRHLFODW2MM/action/citation_signature","submit_replication":"https://pith.science/pith/BKBTX3GWJZRILLGHRHLFODW2MM/action/replication_record"}},"created_at":"2026-07-05T07:28:13.960273+00:00","updated_at":"2026-07-05T07:28:13.960273+00:00"}