{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:6DI6NTJEUZTIVOGAZNWGAGGD3M","short_pith_number":"pith:6DI6NTJE","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"},"canonical_sha256":"f0d1e6cd24a6668ab8c0cb6c6018c3db010d1ee4d6c03d46bbded93656594159","source":{"kind":"arxiv","id":"1711.08946","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.08946","created_at":"2026-05-17T23:55:34Z"},{"alias_kind":"arxiv_version","alias_value":"1711.08946v2","created_at":"2026-05-17T23:55:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.08946","created_at":"2026-05-17T23:55:34Z"},{"alias_kind":"pith_short_12","alias_value":"6DI6NTJEUZTI","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"6DI6NTJEUZTIVOGA","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"6DI6NTJE","created_at":"2026-05-18T12:31:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:6DI6NTJEUZTIVOGAZNWGAGGD3M","target":"record","payload":{"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"},"canonical_sha256":"f0d1e6cd24a6668ab8c0cb6c6018c3db010d1ee4d6c03d46bbded93656594159","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"},"source_kind":"arxiv","source_id":"1711.08946","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:55:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CdQRo/wv/3sI826vBJaoO+umn2MzX9jlfGhIC3s2etG9/5NqZT6K8ndYM0YNbwT9CXSV5PXFsySbvvwsYvcWAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T05:14:19.584202Z"},"content_sha256":"418465bd4e3d0bef52bcffa74e3a7cda9a0224a77ccc81c1ae4de85a14e71f5a","schema_version":"1.0","event_id":"sha256:418465bd4e3d0bef52bcffa74e3a7cda9a0224a77ccc81c1ae4de85a14e71f5a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:6DI6NTJEUZTIVOGAZNWGAGGD3M","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:55:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DNu7lUhqZnVWDh2r5M2GLXMSKkXE13xV+SqBpl0g9FRz3s6GFPdr8N8aFfcgv4HADGtilpvTo+pO483KZHiWAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T05:14:19.584771Z"},"content_sha256":"5c666b691c5c550d6451f551ad0f1cbffccba7d163d2daf741446d767dd1767d","schema_version":"1.0","event_id":"sha256:5c666b691c5c550d6451f551ad0f1cbffccba7d163d2daf741446d767dd1767d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6DI6NTJEUZTIVOGAZNWGAGGD3M/bundle.json","state_url":"https://pith.science/pith/6DI6NTJEUZTIVOGAZNWGAGGD3M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6DI6NTJEUZTIVOGAZNWGAGGD3M/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-26T05:14:19Z","links":{"resolver":"https://pith.science/pith/6DI6NTJEUZTIVOGAZNWGAGGD3M","bundle":"https://pith.science/pith/6DI6NTJEUZTIVOGAZNWGAGGD3M/bundle.json","state":"https://pith.science/pith/6DI6NTJEUZTIVOGAZNWGAGGD3M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6DI6NTJEUZTIVOGAZNWGAGGD3M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:6DI6NTJEUZTIVOGAZNWGAGGD3M","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":"c29f7250ab50f4713b0f1c91ff67631211d3f0d1e24283fca00ecc23f5104748","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-24T12:45:30Z","title_canon_sha256":"b5c84f053d422b9e390045c92d80ad6a642905239e0a665f230e88388f47ff22"},"schema_version":"1.0","source":{"id":"1711.08946","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.08946","created_at":"2026-05-17T23:55:34Z"},{"alias_kind":"arxiv_version","alias_value":"1711.08946v2","created_at":"2026-05-17T23:55:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.08946","created_at":"2026-05-17T23:55:34Z"},{"alias_kind":"pith_short_12","alias_value":"6DI6NTJEUZTI","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"6DI6NTJEUZTIVOGA","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"6DI6NTJE","created_at":"2026-05-18T12:31:03Z"}],"graph_snapshots":[{"event_id":"sha256:5c666b691c5c550d6451f551ad0f1cbffccba7d163d2daf741446d767dd1767d","target":"graph","created_at":"2026-05-17T23:55:34Z","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"},"paper":{"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","authors_text":"Arash Tavakoli, Fabio Pardo, Petar Kormushev","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-24T12:45:30Z","title":"Action Branching Architectures for Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.08946","kind":"arxiv","version":2},"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":"sha256:418465bd4e3d0bef52bcffa74e3a7cda9a0224a77ccc81c1ae4de85a14e71f5a","target":"record","created_at":"2026-05-17T23:55:34Z","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":"c29f7250ab50f4713b0f1c91ff67631211d3f0d1e24283fca00ecc23f5104748","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-24T12:45:30Z","title_canon_sha256":"b5c84f053d422b9e390045c92d80ad6a642905239e0a665f230e88388f47ff22"},"schema_version":"1.0","source":{"id":"1711.08946","kind":"arxiv","version":2}},"canonical_sha256":"f0d1e6cd24a6668ab8c0cb6c6018c3db010d1ee4d6c03d46bbded93656594159","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0d1e6cd24a6668ab8c0cb6c6018c3db010d1ee4d6c03d46bbded93656594159","first_computed_at":"2026-05-17T23:55:34.647050Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:34.647050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L1/R63B9a0DJLlldj7w700dLkfBW0X2aPRdpgzE82owVDKkEKHRVM7Rkv5wPqQnFq+Xqoyx3VE123lIoeq+3Bw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:34.647540Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.08946","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:418465bd4e3d0bef52bcffa74e3a7cda9a0224a77ccc81c1ae4de85a14e71f5a","sha256:5c666b691c5c550d6451f551ad0f1cbffccba7d163d2daf741446d767dd1767d"],"state_sha256":"550a60ce0bae2e250fd4f8fa44afdef25105c3863e32123fd5f64a2f5bf9fd8f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ysx+4a4Ye74xHV03KtSV1pLTCfJCzoEaesm27hKtQetC2X9AaUqxjOjSkfOeIoRYNwkPmamPgJ6wuFsRHXF4DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T05:14:19.586991Z","bundle_sha256":"f772bd783fadea487eb57bf7871c33783b55cc8efd9f777ac7bbbe8f0edf7866"}}