{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:6DI6NTJEUZTIVOGAZNWGAGGD3M","short_pith_number":"pith:6DI6NTJE","schema_version":"1.0","canonical_sha256":"f0d1e6cd24a6668ab8c0cb6c6018c3db010d1ee4d6c03d46bbded93656594159","source":{"kind":"arxiv","id":"1711.08946","version":2},"attestation_state":"computed","paper":{"title":"Action Branching Architectures for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Arash Tavakoli, Fabio Pardo, Petar Kormushev","submitted_at":"2017-11-24T12:45:30Z","abstract_excerpt":"Discrete-action algorithms have been central to numerous recent successes of deep reinforcement learning. However, applying these algorithms to high-dimensional action tasks requires tackling the combinatorial increase of the number of possible actions with the number of action dimensions. This problem is further exacerbated for continuous-action tasks that require fine control of actions via discretization. In this paper, we propose a novel neural architecture featuring a shared decision module followed by several network branches, one for each action dimension. This approach achieves a linea"},"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":"1711.08946","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-24T12:45:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b5c84f053d422b9e390045c92d80ad6a642905239e0a665f230e88388f47ff22","abstract_canon_sha256":"c29f7250ab50f4713b0f1c91ff67631211d3f0d1e24283fca00ecc23f5104748"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:34.647540Z","signature_b64":"L1/R63B9a0DJLlldj7w700dLkfBW0X2aPRdpgzE82owVDKkEKHRVM7Rkv5wPqQnFq+Xqoyx3VE123lIoeq+3Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0d1e6cd24a6668ab8c0cb6c6018c3db010d1ee4d6c03d46bbded93656594159","last_reissued_at":"2026-05-17T23:55:34.647050Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:34.647050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Action Branching Architectures for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Arash Tavakoli, Fabio Pardo, Petar Kormushev","submitted_at":"2017-11-24T12:45:30Z","abstract_excerpt":"Discrete-action algorithms have been central to numerous recent successes of deep reinforcement learning. However, applying these algorithms to high-dimensional action tasks requires tackling the combinatorial increase of the number of possible actions with the number of action dimensions. This problem is further exacerbated for continuous-action tasks that require fine control of actions via discretization. In this paper, we propose a novel neural architecture featuring a shared decision module followed by several network branches, one for each action dimension. This approach achieves a linea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.08946","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1711.08946","created_at":"2026-05-17T23:55:34.647121+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.08946v2","created_at":"2026-05-17T23:55:34.647121+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.08946","created_at":"2026-05-17T23:55:34.647121+00:00"},{"alias_kind":"pith_short_12","alias_value":"6DI6NTJEUZTI","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_16","alias_value":"6DI6NTJEUZTIVOGA","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_8","alias_value":"6DI6NTJE","created_at":"2026-05-18T12:31:03.183658+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/6DI6NTJEUZTIVOGAZNWGAGGD3M","json":"https://pith.science/pith/6DI6NTJEUZTIVOGAZNWGAGGD3M.json","graph_json":"https://pith.science/api/pith-number/6DI6NTJEUZTIVOGAZNWGAGGD3M/graph.json","events_json":"https://pith.science/api/pith-number/6DI6NTJEUZTIVOGAZNWGAGGD3M/events.json","paper":"https://pith.science/paper/6DI6NTJE"},"agent_actions":{"view_html":"https://pith.science/pith/6DI6NTJEUZTIVOGAZNWGAGGD3M","download_json":"https://pith.science/pith/6DI6NTJEUZTIVOGAZNWGAGGD3M.json","view_paper":"https://pith.science/paper/6DI6NTJE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.08946&json=true","fetch_graph":"https://pith.science/api/pith-number/6DI6NTJEUZTIVOGAZNWGAGGD3M/graph.json","fetch_events":"https://pith.science/api/pith-number/6DI6NTJEUZTIVOGAZNWGAGGD3M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6DI6NTJEUZTIVOGAZNWGAGGD3M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6DI6NTJEUZTIVOGAZNWGAGGD3M/action/storage_attestation","attest_author":"https://pith.science/pith/6DI6NTJEUZTIVOGAZNWGAGGD3M/action/author_attestation","sign_citation":"https://pith.science/pith/6DI6NTJEUZTIVOGAZNWGAGGD3M/action/citation_signature","submit_replication":"https://pith.science/pith/6DI6NTJEUZTIVOGAZNWGAGGD3M/action/replication_record"}},"created_at":"2026-05-17T23:55:34.647121+00:00","updated_at":"2026-05-17T23:55:34.647121+00:00"}