{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:DKXXCPEEV4Q6KYSTIRGESJ3NRM","short_pith_number":"pith:DKXXCPEE","canonical_record":{"source":{"id":"1712.00579","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-02T09:46:33Z","cross_cats_sorted":[],"title_canon_sha256":"0d4bbf46ebbb43a561b5a658514ed8ab6ed8d3da30106ba72a35e72b50b12214","abstract_canon_sha256":"55fc23b8c1093cc2782bd661339caadb12bc2d4f33d087ef8ec43bd26f986e85"},"schema_version":"1.0"},"canonical_sha256":"1aaf713c84af21e56253444c49276d8b21570e29afef4fbe8c9e95df4acc3d9a","source":{"kind":"arxiv","id":"1712.00579","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.00579","created_at":"2026-05-18T00:29:04Z"},{"alias_kind":"arxiv_version","alias_value":"1712.00579v1","created_at":"2026-05-18T00:29:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.00579","created_at":"2026-05-18T00:29:04Z"},{"alias_kind":"pith_short_12","alias_value":"DKXXCPEEV4Q6","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"DKXXCPEEV4Q6KYST","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"DKXXCPEE","created_at":"2026-05-18T12:31:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:DKXXCPEEV4Q6KYSTIRGESJ3NRM","target":"record","payload":{"canonical_record":{"source":{"id":"1712.00579","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-02T09:46:33Z","cross_cats_sorted":[],"title_canon_sha256":"0d4bbf46ebbb43a561b5a658514ed8ab6ed8d3da30106ba72a35e72b50b12214","abstract_canon_sha256":"55fc23b8c1093cc2782bd661339caadb12bc2d4f33d087ef8ec43bd26f986e85"},"schema_version":"1.0"},"canonical_sha256":"1aaf713c84af21e56253444c49276d8b21570e29afef4fbe8c9e95df4acc3d9a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:04.811907Z","signature_b64":"zLO4CNV7rm2cWrOCibxhCoPJNNH6i8yri2RFkJUYFmYD4kW/IGQqj4j59ie8Sd5lZx0DcLzQVeTXmZb//7MXDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1aaf713c84af21e56253444c49276d8b21570e29afef4fbe8c9e95df4acc3d9a","last_reissued_at":"2026-05-18T00:29:04.811147Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:04.811147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.00579","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":"2026-05-18T00:29:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4+1lTaBOmpsmXFeAJINeKoDdpUF0zyHaNA84QU39eZPo0SUlo8nW2H1g/ByIVg/zExpd6x58tmHuqihENqA2Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T07:58:10.814999Z"},"content_sha256":"e2552d330b4f4559e911dfc976b730780f85dde8c217bde5e819908b02bc8619","schema_version":"1.0","event_id":"sha256:e2552d330b4f4559e911dfc976b730780f85dde8c217bde5e819908b02bc8619"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:DKXXCPEEV4Q6KYSTIRGESJ3NRM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Online Reinforcement Learning in Stochastic Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chen-Yu Wei, Chi-Jen Lu, Yi-Te Hong","submitted_at":"2017-12-02T09:46:33Z","abstract_excerpt":"We study online reinforcement learning in average-reward stochastic games (SGs). An SG models a two-player zero-sum game in a Markov environment, where state transitions and one-step payoffs are determined simultaneously by a learner and an adversary. We propose the UCSG algorithm that achieves a sublinear regret compared to the game value when competing with an arbitrary opponent. This result improves previous ones under the same setting. The regret bound has a dependency on the diameter, which is an intrinsic value related to the mixing property of SGs. If we let the opponent play an optimis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.00579","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":"2026-05-18T00:29:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WFKmpzMX3uVtdD23bhkogqa9YTm0O5MM1TQf1C2ycmbd9zjpJqLMnHjT56aVIKwQnWX/RhIbxvAnVcV7lDKkAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T07:58:10.815727Z"},"content_sha256":"7fd68378beb8211c28c482bf99bb2420c5ccee235a9cc6674282e4c1460bbb2a","schema_version":"1.0","event_id":"sha256:7fd68378beb8211c28c482bf99bb2420c5ccee235a9cc6674282e4c1460bbb2a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DKXXCPEEV4Q6KYSTIRGESJ3NRM/bundle.json","state_url":"https://pith.science/pith/DKXXCPEEV4Q6KYSTIRGESJ3NRM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DKXXCPEEV4Q6KYSTIRGESJ3NRM/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":"2026-06-11T07:58:10Z","links":{"resolver":"https://pith.science/pith/DKXXCPEEV4Q6KYSTIRGESJ3NRM","bundle":"https://pith.science/pith/DKXXCPEEV4Q6KYSTIRGESJ3NRM/bundle.json","state":"https://pith.science/pith/DKXXCPEEV4Q6KYSTIRGESJ3NRM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DKXXCPEEV4Q6KYSTIRGESJ3NRM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:DKXXCPEEV4Q6KYSTIRGESJ3NRM","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":"55fc23b8c1093cc2782bd661339caadb12bc2d4f33d087ef8ec43bd26f986e85","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-02T09:46:33Z","title_canon_sha256":"0d4bbf46ebbb43a561b5a658514ed8ab6ed8d3da30106ba72a35e72b50b12214"},"schema_version":"1.0","source":{"id":"1712.00579","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.00579","created_at":"2026-05-18T00:29:04Z"},{"alias_kind":"arxiv_version","alias_value":"1712.00579v1","created_at":"2026-05-18T00:29:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.00579","created_at":"2026-05-18T00:29:04Z"},{"alias_kind":"pith_short_12","alias_value":"DKXXCPEEV4Q6","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"DKXXCPEEV4Q6KYST","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"DKXXCPEE","created_at":"2026-05-18T12:31:10Z"}],"graph_snapshots":[{"event_id":"sha256:7fd68378beb8211c28c482bf99bb2420c5ccee235a9cc6674282e4c1460bbb2a","target":"graph","created_at":"2026-05-18T00:29:04Z","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":"We study online reinforcement learning in average-reward stochastic games (SGs). An SG models a two-player zero-sum game in a Markov environment, where state transitions and one-step payoffs are determined simultaneously by a learner and an adversary. We propose the UCSG algorithm that achieves a sublinear regret compared to the game value when competing with an arbitrary opponent. This result improves previous ones under the same setting. The regret bound has a dependency on the diameter, which is an intrinsic value related to the mixing property of SGs. If we let the opponent play an optimis","authors_text":"Chen-Yu Wei, Chi-Jen Lu, Yi-Te Hong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-02T09:46:33Z","title":"Online Reinforcement Learning in Stochastic Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.00579","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:e2552d330b4f4559e911dfc976b730780f85dde8c217bde5e819908b02bc8619","target":"record","created_at":"2026-05-18T00:29:04Z","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":"55fc23b8c1093cc2782bd661339caadb12bc2d4f33d087ef8ec43bd26f986e85","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-02T09:46:33Z","title_canon_sha256":"0d4bbf46ebbb43a561b5a658514ed8ab6ed8d3da30106ba72a35e72b50b12214"},"schema_version":"1.0","source":{"id":"1712.00579","kind":"arxiv","version":1}},"canonical_sha256":"1aaf713c84af21e56253444c49276d8b21570e29afef4fbe8c9e95df4acc3d9a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1aaf713c84af21e56253444c49276d8b21570e29afef4fbe8c9e95df4acc3d9a","first_computed_at":"2026-05-18T00:29:04.811147Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:29:04.811147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zLO4CNV7rm2cWrOCibxhCoPJNNH6i8yri2RFkJUYFmYD4kW/IGQqj4j59ie8Sd5lZx0DcLzQVeTXmZb//7MXDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:29:04.811907Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.00579","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2552d330b4f4559e911dfc976b730780f85dde8c217bde5e819908b02bc8619","sha256:7fd68378beb8211c28c482bf99bb2420c5ccee235a9cc6674282e4c1460bbb2a"],"state_sha256":"7a7d2eb278a75360555d8c38df9f8dee9a732f19c21310704071a48ad35aabfd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y/yyLOD9ajdB7RsUpV5RUNtVH8jY+JJoSe/Lck/8xyQ9DeOwnFHJKTD2iyPC+0sQCu0suvpVK/jEhlj/TPUpDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T07:58:10.820038Z","bundle_sha256":"d730fda421bc2e8b1278ec060f444eebb94543efa80b4941bdc313124d456022"}}