{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:L2SSWZILMMOUIJXIUV7C36XGRC","short_pith_number":"pith:L2SSWZIL","canonical_record":{"source":{"id":"2009.06373","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-10T14:20:33Z","cross_cats_sorted":["cs.GT","stat.ML"],"title_canon_sha256":"a02429ff34250c1bd0ebe357e0e3a2cbd403c40cb1984f8c400830ca0dae249d","abstract_canon_sha256":"0b6cce3e666acf70763451c025012e08ceb09094ff0967c21f9ff9c5e2d58b3c"},"schema_version":"1.0"},"canonical_sha256":"5ea52b650b631d4426e8a57e2dfae6889b3ba8e968faf5e30c6297531c6441da","source":{"kind":"arxiv","id":"2009.06373","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.06373","created_at":"2026-07-05T01:35:07Z"},{"alias_kind":"arxiv_version","alias_value":"2009.06373v1","created_at":"2026-07-05T01:35:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.06373","created_at":"2026-07-05T01:35:07Z"},{"alias_kind":"pith_short_12","alias_value":"L2SSWZILMMOU","created_at":"2026-07-05T01:35:07Z"},{"alias_kind":"pith_short_16","alias_value":"L2SSWZILMMOUIJXI","created_at":"2026-07-05T01:35:07Z"},{"alias_kind":"pith_short_8","alias_value":"L2SSWZIL","created_at":"2026-07-05T01:35:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:L2SSWZILMMOUIJXIUV7C36XGRC","target":"record","payload":{"canonical_record":{"source":{"id":"2009.06373","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-10T14:20:33Z","cross_cats_sorted":["cs.GT","stat.ML"],"title_canon_sha256":"a02429ff34250c1bd0ebe357e0e3a2cbd403c40cb1984f8c400830ca0dae249d","abstract_canon_sha256":"0b6cce3e666acf70763451c025012e08ceb09094ff0967c21f9ff9c5e2d58b3c"},"schema_version":"1.0"},"canonical_sha256":"5ea52b650b631d4426e8a57e2dfae6889b3ba8e968faf5e30c6297531c6441da","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:35:07.909529Z","signature_b64":"Gf5hGjGcUjN2BsHU5dfiZAwxdMzZTstj99TLzG95fYeN4mzPLkenA8y0fRXSbXrQvt8Kgg3alLy5g4eLrU1WDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ea52b650b631d4426e8a57e2dfae6889b3ba8e968faf5e30c6297531c6441da","last_reissued_at":"2026-07-05T01:35:07.909169Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:35:07.909169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2009.06373","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":"2026-07-05T01:35:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tAMHTPWImfk2DuSmxYGtpBi4L7f/+TF4TCQ4eAiVdXwlpWyUfId6IGIvlY/pB6O7qwR7pxMR8kA7MWMn8dVjBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:06:22.691506Z"},"content_sha256":"5d9367c1fd2a8a9a06e13225d179c02b4e0aa369b272fdf4b018d67d13573dfc","schema_version":"1.0","event_id":"sha256:5d9367c1fd2a8a9a06e13225d179c02b4e0aa369b272fdf4b018d67d13573dfc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:L2SSWZILMMOUIJXIUV7C36XGRC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RLCFR: Minimize Counterfactual Regret by Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fengwei Jia, Huale Li, Jiajia Zhang, Shuhan Qi, Xuan Wang, Yifan Li, Yulin Wu","submitted_at":"2020-09-10T14:20:33Z","abstract_excerpt":"Counterfactual regret minimization (CFR) is a popular method to deal with decision-making problems of two-player zero-sum games with imperfect information. Unlike existing studies that mostly explore for solving larger scale problems or accelerating solution efficiency, we propose a framework, RLCFR, which aims at improving the generalization ability of the CFR method. In the RLCFR, the game strategy is solved by the CFR in a reinforcement learning framework. And the dynamic procedure of iterative interactive strategy updating is modeled as a Markov decision process (MDP). Our method, RLCFR, t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.06373","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2009.06373/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:35:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/JpRFIx5IbZbzPplPr7zY5p9/cRuW00G0IcHrhtKBmFHyJVr9eJNUTThS3Pwyt1Sk2dyC2j9jZfKq8IjAP5DAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:06:22.691883Z"},"content_sha256":"136c95ab07d8be8749940737fa7dbc0ae4bbc712f3eac4f1b79bd00f358daca2","schema_version":"1.0","event_id":"sha256:136c95ab07d8be8749940737fa7dbc0ae4bbc712f3eac4f1b79bd00f358daca2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L2SSWZILMMOUIJXIUV7C36XGRC/bundle.json","state_url":"https://pith.science/pith/L2SSWZILMMOUIJXIUV7C36XGRC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L2SSWZILMMOUIJXIUV7C36XGRC/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":"2026-07-06T23:06:22Z","links":{"resolver":"https://pith.science/pith/L2SSWZILMMOUIJXIUV7C36XGRC","bundle":"https://pith.science/pith/L2SSWZILMMOUIJXIUV7C36XGRC/bundle.json","state":"https://pith.science/pith/L2SSWZILMMOUIJXIUV7C36XGRC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L2SSWZILMMOUIJXIUV7C36XGRC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:L2SSWZILMMOUIJXIUV7C36XGRC","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":"0b6cce3e666acf70763451c025012e08ceb09094ff0967c21f9ff9c5e2d58b3c","cross_cats_sorted":["cs.GT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-10T14:20:33Z","title_canon_sha256":"a02429ff34250c1bd0ebe357e0e3a2cbd403c40cb1984f8c400830ca0dae249d"},"schema_version":"1.0","source":{"id":"2009.06373","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.06373","created_at":"2026-07-05T01:35:07Z"},{"alias_kind":"arxiv_version","alias_value":"2009.06373v1","created_at":"2026-07-05T01:35:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.06373","created_at":"2026-07-05T01:35:07Z"},{"alias_kind":"pith_short_12","alias_value":"L2SSWZILMMOU","created_at":"2026-07-05T01:35:07Z"},{"alias_kind":"pith_short_16","alias_value":"L2SSWZILMMOUIJXI","created_at":"2026-07-05T01:35:07Z"},{"alias_kind":"pith_short_8","alias_value":"L2SSWZIL","created_at":"2026-07-05T01:35:07Z"}],"graph_snapshots":[{"event_id":"sha256:136c95ab07d8be8749940737fa7dbc0ae4bbc712f3eac4f1b79bd00f358daca2","target":"graph","created_at":"2026-07-05T01:35:07Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2009.06373/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Counterfactual regret minimization (CFR) is a popular method to deal with decision-making problems of two-player zero-sum games with imperfect information. Unlike existing studies that mostly explore for solving larger scale problems or accelerating solution efficiency, we propose a framework, RLCFR, which aims at improving the generalization ability of the CFR method. In the RLCFR, the game strategy is solved by the CFR in a reinforcement learning framework. And the dynamic procedure of iterative interactive strategy updating is modeled as a Markov decision process (MDP). Our method, RLCFR, t","authors_text":"Fengwei Jia, Huale Li, Jiajia Zhang, Shuhan Qi, Xuan Wang, Yifan Li, Yulin Wu","cross_cats":["cs.GT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-10T14:20:33Z","title":"RLCFR: Minimize Counterfactual Regret by Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.06373","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":"sha256:5d9367c1fd2a8a9a06e13225d179c02b4e0aa369b272fdf4b018d67d13573dfc","target":"record","created_at":"2026-07-05T01:35:07Z","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":"0b6cce3e666acf70763451c025012e08ceb09094ff0967c21f9ff9c5e2d58b3c","cross_cats_sorted":["cs.GT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-10T14:20:33Z","title_canon_sha256":"a02429ff34250c1bd0ebe357e0e3a2cbd403c40cb1984f8c400830ca0dae249d"},"schema_version":"1.0","source":{"id":"2009.06373","kind":"arxiv","version":1}},"canonical_sha256":"5ea52b650b631d4426e8a57e2dfae6889b3ba8e968faf5e30c6297531c6441da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ea52b650b631d4426e8a57e2dfae6889b3ba8e968faf5e30c6297531c6441da","first_computed_at":"2026-07-05T01:35:07.909169Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:35:07.909169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gf5hGjGcUjN2BsHU5dfiZAwxdMzZTstj99TLzG95fYeN4mzPLkenA8y0fRXSbXrQvt8Kgg3alLy5g4eLrU1WDw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:35:07.909529Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.06373","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d9367c1fd2a8a9a06e13225d179c02b4e0aa369b272fdf4b018d67d13573dfc","sha256:136c95ab07d8be8749940737fa7dbc0ae4bbc712f3eac4f1b79bd00f358daca2"],"state_sha256":"8fe1335b0356353d95ec608cab3b248307869174e960f98e1534651740048275"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ghMoG6rew5/66PEueNSP17Bz7esnNY8ABlEnfRmAd+oDGttIOixQZfxXXAuwTzwmsLWYvf0tUGBp3annyDf1Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T23:06:22.693823Z","bundle_sha256":"74e0df618ed0bbea7523dfd9534cde26b40a5aad0217ec31e5c13d54e348db85"}}