{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:ESZZ7R77PUR6WD4NLTRCXCFLJN","short_pith_number":"pith:ESZZ7R77","canonical_record":{"source":{"id":"1805.09613","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-24T11:33:49Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO","cs.SY"],"title_canon_sha256":"20f17949905343727da4eb5ad0b985e91ac2935c77848aab69c4d68d7cc4b769","abstract_canon_sha256":"b44d52c8c4de48c61243f335b1745c55cb6519775790c8c1937ac260f974888a"},"schema_version":"1.0"},"canonical_sha256":"24b39fc7ff7d23eb0f8d5ce22b88ab4b7f89c8eab2ec00164a505807a4137559","source":{"kind":"arxiv","id":"1805.09613","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.09613","created_at":"2026-05-18T00:15:03Z"},{"alias_kind":"arxiv_version","alias_value":"1805.09613v1","created_at":"2026-05-18T00:15:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09613","created_at":"2026-05-18T00:15:03Z"},{"alias_kind":"pith_short_12","alias_value":"ESZZ7R77PUR6","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"ESZZ7R77PUR6WD4N","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"ESZZ7R77","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:ESZZ7R77PUR6WD4NLTRCXCFLJN","target":"record","payload":{"canonical_record":{"source":{"id":"1805.09613","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-24T11:33:49Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO","cs.SY"],"title_canon_sha256":"20f17949905343727da4eb5ad0b985e91ac2935c77848aab69c4d68d7cc4b769","abstract_canon_sha256":"b44d52c8c4de48c61243f335b1745c55cb6519775790c8c1937ac260f974888a"},"schema_version":"1.0"},"canonical_sha256":"24b39fc7ff7d23eb0f8d5ce22b88ab4b7f89c8eab2ec00164a505807a4137559","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:03.403569Z","signature_b64":"Vwfihvk8JxExMfzHtzUM930Z24ZfcvdXllRhF1WSwisdQ1TlHgzgtN9eWX7L0nEfS9nx/XDflsqSVotwbCuiDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24b39fc7ff7d23eb0f8d5ce22b88ab4b7f89c8eab2ec00164a505807a4137559","last_reissued_at":"2026-05-18T00:15:03.400137Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:03.400137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.09613","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:15:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6etMbEgzp8nxbn5pdZX6m6oCIoqIK9/rIhDIzRChZJmXjliVhVeo1XVfdgNmhYVZ0YULThm6bSEfJPwPc9TUDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-23T19:21:38.093625Z"},"content_sha256":"5c2c2f21b20b8c41b0e65895681ea5c6a42218830a77af4e80dcd59008fb18c4","schema_version":"1.0","event_id":"sha256:5c2c2f21b20b8c41b0e65895681ea5c6a42218830a77af4e80dcd59008fb18c4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:ESZZ7R77PUR6WD4NLTRCXCFLJN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A0C: Alpha Zero in Continuous Action Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO","cs.SY"],"primary_cat":"stat.ML","authors_text":"Aske Plaat, Catholijn M. Jonker, Joost Broekens, Thomas M. Moerland","submitted_at":"2018-05-24T11:33:49Z","abstract_excerpt":"A core novelty of Alpha Zero is the interleaving of tree search and deep learning, which has proven very successful in board games like Chess, Shogi and Go. These games have a discrete action space. However, many real-world reinforcement learning domains have continuous action spaces, for example in robotic control, navigation and self-driving cars. This paper presents the necessary theoretical extensions of Alpha Zero to deal with continuous action space. We also provide some preliminary experiments on the Pendulum swing-up task, empirically showing the feasibility of our approach. Thereby, t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09613","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":""},"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":"2026-05-18T00:15:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zXOJLJwyPYcG3SJgUAGbSfL7KsmUPf8TfY6EcFjcy2ryzWh3IFFPgz2KOplj51bY7TS2imi2exhXuOK2bUbDDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-23T19:21:38.093981Z"},"content_sha256":"2a82b370fc6141842c2708731be1cbe599c08210f5ad54e93d0034e7f2380751","schema_version":"1.0","event_id":"sha256:2a82b370fc6141842c2708731be1cbe599c08210f5ad54e93d0034e7f2380751"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ESZZ7R77PUR6WD4NLTRCXCFLJN/bundle.json","state_url":"https://pith.science/pith/ESZZ7R77PUR6WD4NLTRCXCFLJN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ESZZ7R77PUR6WD4NLTRCXCFLJN/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":"2026-06-23T19:21:38Z","links":{"resolver":"https://pith.science/pith/ESZZ7R77PUR6WD4NLTRCXCFLJN","bundle":"https://pith.science/pith/ESZZ7R77PUR6WD4NLTRCXCFLJN/bundle.json","state":"https://pith.science/pith/ESZZ7R77PUR6WD4NLTRCXCFLJN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ESZZ7R77PUR6WD4NLTRCXCFLJN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ESZZ7R77PUR6WD4NLTRCXCFLJN","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":"b44d52c8c4de48c61243f335b1745c55cb6519775790c8c1937ac260f974888a","cross_cats_sorted":["cs.AI","cs.LG","cs.RO","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-24T11:33:49Z","title_canon_sha256":"20f17949905343727da4eb5ad0b985e91ac2935c77848aab69c4d68d7cc4b769"},"schema_version":"1.0","source":{"id":"1805.09613","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.09613","created_at":"2026-05-18T00:15:03Z"},{"alias_kind":"arxiv_version","alias_value":"1805.09613v1","created_at":"2026-05-18T00:15:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09613","created_at":"2026-05-18T00:15:03Z"},{"alias_kind":"pith_short_12","alias_value":"ESZZ7R77PUR6","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"ESZZ7R77PUR6WD4N","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"ESZZ7R77","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:2a82b370fc6141842c2708731be1cbe599c08210f5ad54e93d0034e7f2380751","target":"graph","created_at":"2026-05-18T00:15:03Z","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":"A core novelty of Alpha Zero is the interleaving of tree search and deep learning, which has proven very successful in board games like Chess, Shogi and Go. These games have a discrete action space. However, many real-world reinforcement learning domains have continuous action spaces, for example in robotic control, navigation and self-driving cars. This paper presents the necessary theoretical extensions of Alpha Zero to deal with continuous action space. We also provide some preliminary experiments on the Pendulum swing-up task, empirically showing the feasibility of our approach. Thereby, t","authors_text":"Aske Plaat, Catholijn M. Jonker, Joost Broekens, Thomas M. Moerland","cross_cats":["cs.AI","cs.LG","cs.RO","cs.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-24T11:33:49Z","title":"A0C: Alpha Zero in Continuous Action Space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09613","kind":"arxiv","version":1},"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":"sha256:5c2c2f21b20b8c41b0e65895681ea5c6a42218830a77af4e80dcd59008fb18c4","target":"record","created_at":"2026-05-18T00:15:03Z","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":"b44d52c8c4de48c61243f335b1745c55cb6519775790c8c1937ac260f974888a","cross_cats_sorted":["cs.AI","cs.LG","cs.RO","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-24T11:33:49Z","title_canon_sha256":"20f17949905343727da4eb5ad0b985e91ac2935c77848aab69c4d68d7cc4b769"},"schema_version":"1.0","source":{"id":"1805.09613","kind":"arxiv","version":1}},"canonical_sha256":"24b39fc7ff7d23eb0f8d5ce22b88ab4b7f89c8eab2ec00164a505807a4137559","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24b39fc7ff7d23eb0f8d5ce22b88ab4b7f89c8eab2ec00164a505807a4137559","first_computed_at":"2026-05-18T00:15:03.400137Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:03.400137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vwfihvk8JxExMfzHtzUM930Z24ZfcvdXllRhF1WSwisdQ1TlHgzgtN9eWX7L0nEfS9nx/XDflsqSVotwbCuiDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:03.403569Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.09613","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c2c2f21b20b8c41b0e65895681ea5c6a42218830a77af4e80dcd59008fb18c4","sha256:2a82b370fc6141842c2708731be1cbe599c08210f5ad54e93d0034e7f2380751"],"state_sha256":"b33661349d5807cf12d4d6c0ec5a124c4c3b2b4c4a9844ceaa68261542c88d25"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TcpWDjjZgC479EjhVPs/oaXGd1WAUAFNEJYxUeKX/mOoGT9s4vahjrsPrNEbsDo6CyEFZWjRBcQYCD9niezGBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-23T19:21:38.096612Z","bundle_sha256":"f0ab577a088063e65776fd42fe2b1817cac3c2a297c6a06c5c8a9bea6e4e1edc"}}