{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:V75DVKTYTXVVMXZV2DULIXOYMS","short_pith_number":"pith:V75DVKTY","canonical_record":{"source":{"id":"1901.08925","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T08:28:04Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"abe6722a9f90fdf2357c2beeb6f7398987d44aca8a8dae874041a378c47254a9","abstract_canon_sha256":"dc3776fff173dd17594ee7acc14e7890f162735e42fa78220cd94120aa18a057"},"schema_version":"1.0"},"canonical_sha256":"affa3aaa789deb565f35d0e8b45dd864a8ced3486652d1e99051179da593755e","source":{"kind":"arxiv","id":"1901.08925","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.08925","created_at":"2026-05-17T23:53:41Z"},{"alias_kind":"arxiv_version","alias_value":"1901.08925v2","created_at":"2026-05-17T23:53:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08925","created_at":"2026-05-17T23:53:41Z"},{"alias_kind":"pith_short_12","alias_value":"V75DVKTYTXVV","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"V75DVKTYTXVVMXZV","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"V75DVKTY","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:V75DVKTYTXVVMXZV2DULIXOYMS","target":"record","payload":{"canonical_record":{"source":{"id":"1901.08925","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T08:28:04Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"abe6722a9f90fdf2357c2beeb6f7398987d44aca8a8dae874041a378c47254a9","abstract_canon_sha256":"dc3776fff173dd17594ee7acc14e7890f162735e42fa78220cd94120aa18a057"},"schema_version":"1.0"},"canonical_sha256":"affa3aaa789deb565f35d0e8b45dd864a8ced3486652d1e99051179da593755e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:41.111191Z","signature_b64":"xkOY8A0GcODhwy9x5Rt3pGv3u+q89cJ35g2Xw7ZeVGsbA4elxIYdTz+A/P03FlWRH8HbQ7i7nlB2v/L9WeI/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"affa3aaa789deb565f35d0e8b45dd864a8ced3486652d1e99051179da593755e","last_reissued_at":"2026-05-17T23:53:41.110779Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:41.110779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.08925","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":"2026-05-17T23:53:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rvpbg0tuW2zwrMHdYo+nDx/ItXAItI4CXNgW7o1qercLTw4f0EhVe5X6l27iXx17AXHRORZtyvPsoxm7m94QAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T10:45:50.736078Z"},"content_sha256":"776b1fd0e644e336c25d74cab9c0669ef8e62ac7b280debf46123d06af3cb6e5","schema_version":"1.0","event_id":"sha256:776b1fd0e644e336c25d74cab9c0669ef8e62ac7b280debf46123d06af3cb6e5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:V75DVKTYTXVVMXZV2DULIXOYMS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Combinational Q-Learning for Dou Di Zhu","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Baisong Guo, Cewu Lu, Liangwei Li, Weiming Wang, Yang You","submitted_at":"2019-01-24T08:28:04Z","abstract_excerpt":"Deep reinforcement learning (DRL) has gained a lot of attention in recent years, and has been proven to be able to play Atari games and Go at or above human levels. However, those games are assumed to have a small fixed number of actions and could be trained with a simple CNN network. In this paper, we study a special class of Asian popular card games called Dou Di Zhu, in which two adversarial groups of agents must consider numerous card combinations at each time step, leading to huge number of actions. We propose a novel method to handle combinatorial actions, which we call combinational Q-l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08925","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":"2026-05-17T23:53:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YVIpiXE0zcEh8IlLNug8oPW9n6s5L0W5ONdapQ3u/PT/Bsz1Q38Ajp7UonF9x8qyLASjesiPwy6EpudynyMPBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T10:45:50.736452Z"},"content_sha256":"0ee5fd537096679746fbdbd3ad3cefea5d447fb0f062b4330bb64eb7d2424f60","schema_version":"1.0","event_id":"sha256:0ee5fd537096679746fbdbd3ad3cefea5d447fb0f062b4330bb64eb7d2424f60"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V75DVKTYTXVVMXZV2DULIXOYMS/bundle.json","state_url":"https://pith.science/pith/V75DVKTYTXVVMXZV2DULIXOYMS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V75DVKTYTXVVMXZV2DULIXOYMS/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":"2026-05-28T10:45:50Z","links":{"resolver":"https://pith.science/pith/V75DVKTYTXVVMXZV2DULIXOYMS","bundle":"https://pith.science/pith/V75DVKTYTXVVMXZV2DULIXOYMS/bundle.json","state":"https://pith.science/pith/V75DVKTYTXVVMXZV2DULIXOYMS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V75DVKTYTXVVMXZV2DULIXOYMS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:V75DVKTYTXVVMXZV2DULIXOYMS","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":"dc3776fff173dd17594ee7acc14e7890f162735e42fa78220cd94120aa18a057","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T08:28:04Z","title_canon_sha256":"abe6722a9f90fdf2357c2beeb6f7398987d44aca8a8dae874041a378c47254a9"},"schema_version":"1.0","source":{"id":"1901.08925","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.08925","created_at":"2026-05-17T23:53:41Z"},{"alias_kind":"arxiv_version","alias_value":"1901.08925v2","created_at":"2026-05-17T23:53:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08925","created_at":"2026-05-17T23:53:41Z"},{"alias_kind":"pith_short_12","alias_value":"V75DVKTYTXVV","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"V75DVKTYTXVVMXZV","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"V75DVKTY","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:0ee5fd537096679746fbdbd3ad3cefea5d447fb0f062b4330bb64eb7d2424f60","target":"graph","created_at":"2026-05-17T23:53:41Z","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":"Deep reinforcement learning (DRL) has gained a lot of attention in recent years, and has been proven to be able to play Atari games and Go at or above human levels. However, those games are assumed to have a small fixed number of actions and could be trained with a simple CNN network. In this paper, we study a special class of Asian popular card games called Dou Di Zhu, in which two adversarial groups of agents must consider numerous card combinations at each time step, leading to huge number of actions. We propose a novel method to handle combinatorial actions, which we call combinational Q-l","authors_text":"Baisong Guo, Cewu Lu, Liangwei Li, Weiming Wang, Yang You","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T08:28:04Z","title":"Combinational Q-Learning for Dou Di Zhu"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08925","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":"sha256:776b1fd0e644e336c25d74cab9c0669ef8e62ac7b280debf46123d06af3cb6e5","target":"record","created_at":"2026-05-17T23:53:41Z","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":"dc3776fff173dd17594ee7acc14e7890f162735e42fa78220cd94120aa18a057","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T08:28:04Z","title_canon_sha256":"abe6722a9f90fdf2357c2beeb6f7398987d44aca8a8dae874041a378c47254a9"},"schema_version":"1.0","source":{"id":"1901.08925","kind":"arxiv","version":2}},"canonical_sha256":"affa3aaa789deb565f35d0e8b45dd864a8ced3486652d1e99051179da593755e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"affa3aaa789deb565f35d0e8b45dd864a8ced3486652d1e99051179da593755e","first_computed_at":"2026-05-17T23:53:41.110779Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:53:41.110779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xkOY8A0GcODhwy9x5Rt3pGv3u+q89cJ35g2Xw7ZeVGsbA4elxIYdTz+A/P03FlWRH8HbQ7i7nlB2v/L9WeI/AQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:53:41.111191Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.08925","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:776b1fd0e644e336c25d74cab9c0669ef8e62ac7b280debf46123d06af3cb6e5","sha256:0ee5fd537096679746fbdbd3ad3cefea5d447fb0f062b4330bb64eb7d2424f60"],"state_sha256":"82e63931ce265d035c70901172a776ca5533f9456d5c81f03eab56869d0631bf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pk1+/av6hIJjDU+AZkcQ6xszYiyhLJ3PJFTTmkkT6DJy8r80NJQLKEc/dxrJRslxEhrR0l2EmZIE7f2acxUPAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T10:45:50.738529Z","bundle_sha256":"4027ccdf3ec7baf0d30e4d51b471f525f4c92099a222cc0be021338921e5dc6e"}}