{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:Z6HHSDM322J4G5PJYCYTWH66KI","short_pith_number":"pith:Z6HHSDM3","schema_version":"1.0","canonical_sha256":"cf8e790d9bd693c375e9c0b13b1fde523f6c9c528867e57754c89ed823d2ac1d","source":{"kind":"arxiv","id":"2109.05490","version":3},"attestation_state":"computed","paper":{"title":"HyAR: Addressing Discrete-Continuous Action Reinforcement Learning via Hybrid Action Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Boyan Li, Hongyao Tang, Jianye Hao, Li Wang, Pengyi Li, Yan Zheng, Zhaopeng Meng, Zhen Wang","submitted_at":"2021-09-12T11:26:27Z","abstract_excerpt":"Discrete-continuous hybrid action space is a natural setting in many practical problems, such as robot control and game AI. However, most previous Reinforcement Learning (RL) works only demonstrate the success in controlling with either discrete or continuous action space, while seldom take into account the hybrid action space. One naive way to address hybrid action RL is to convert the hybrid action space into a unified homogeneous action space by discretization or continualization, so that conventional RL algorithms can be applied. However, this ignores the underlying structure of hybrid act"},"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":"2109.05490","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-12T11:26:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2c3cd4012c7a21861431455960cfee21c29008eaef9d06ff932911f9fdddd2eb","abstract_canon_sha256":"076f46096f789f3b1e88f522f0b8410fe2e62b8699727fb4ee3092205dd72e33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:34.021770Z","signature_b64":"AssF+D5z2WByBQyh0LRHof7fcv/lAwcHbpi6b056W3d8Tfln0MtvUALahtalu/6HMYgDYRNzmOGX2L5BPp1XAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf8e790d9bd693c375e9c0b13b1fde523f6c9c528867e57754c89ed823d2ac1d","last_reissued_at":"2026-07-05T04:05:34.021235Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:34.021235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HyAR: Addressing Discrete-Continuous Action Reinforcement Learning via Hybrid Action Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Boyan Li, Hongyao Tang, Jianye Hao, Li Wang, Pengyi Li, Yan Zheng, Zhaopeng Meng, Zhen Wang","submitted_at":"2021-09-12T11:26:27Z","abstract_excerpt":"Discrete-continuous hybrid action space is a natural setting in many practical problems, such as robot control and game AI. However, most previous Reinforcement Learning (RL) works only demonstrate the success in controlling with either discrete or continuous action space, while seldom take into account the hybrid action space. One naive way to address hybrid action RL is to convert the hybrid action space into a unified homogeneous action space by discretization or continualization, so that conventional RL algorithms can be applied. However, this ignores the underlying structure of hybrid act"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.05490","kind":"arxiv","version":3},"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/2109.05490/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":"2109.05490","created_at":"2026-07-05T04:05:34.021295+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.05490v3","created_at":"2026-07-05T04:05:34.021295+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.05490","created_at":"2026-07-05T04:05:34.021295+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z6HHSDM322J4","created_at":"2026-07-05T04:05:34.021295+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z6HHSDM322J4G5PJ","created_at":"2026-07-05T04:05:34.021295+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z6HHSDM3","created_at":"2026-07-05T04:05:34.021295+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26574","citing_title":"Revisiting Action Factorization for Complex Action Spaces","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14297","citing_title":"Policy Optimization in Hybrid Discrete-Continuous Action Spaces via Mixed Gradients","ref_index":105,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z6HHSDM322J4G5PJYCYTWH66KI","json":"https://pith.science/pith/Z6HHSDM322J4G5PJYCYTWH66KI.json","graph_json":"https://pith.science/api/pith-number/Z6HHSDM322J4G5PJYCYTWH66KI/graph.json","events_json":"https://pith.science/api/pith-number/Z6HHSDM322J4G5PJYCYTWH66KI/events.json","paper":"https://pith.science/paper/Z6HHSDM3"},"agent_actions":{"view_html":"https://pith.science/pith/Z6HHSDM322J4G5PJYCYTWH66KI","download_json":"https://pith.science/pith/Z6HHSDM322J4G5PJYCYTWH66KI.json","view_paper":"https://pith.science/paper/Z6HHSDM3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.05490&json=true","fetch_graph":"https://pith.science/api/pith-number/Z6HHSDM322J4G5PJYCYTWH66KI/graph.json","fetch_events":"https://pith.science/api/pith-number/Z6HHSDM322J4G5PJYCYTWH66KI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z6HHSDM322J4G5PJYCYTWH66KI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z6HHSDM322J4G5PJYCYTWH66KI/action/storage_attestation","attest_author":"https://pith.science/pith/Z6HHSDM322J4G5PJYCYTWH66KI/action/author_attestation","sign_citation":"https://pith.science/pith/Z6HHSDM322J4G5PJYCYTWH66KI/action/citation_signature","submit_replication":"https://pith.science/pith/Z6HHSDM322J4G5PJYCYTWH66KI/action/replication_record"}},"created_at":"2026-07-05T04:05:34.021295+00:00","updated_at":"2026-07-05T04:05:34.021295+00:00"}