{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:H5YXYWFN2Q5QBXO73G77YCMGOP","short_pith_number":"pith:H5YXYWFN","canonical_record":{"source":{"id":"2111.11743","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2021-11-23T09:27:20Z","cross_cats_sorted":["cs.LG","math.DS"],"title_canon_sha256":"36e5f8027585d90eaff37127d4c037138ffaf8813a69b61f2dd4982e47aa0a6c","abstract_canon_sha256":"4f03a9a4db93fe32349b55f277520d93e7ad0fbad328b51551b09ae13cdaaef2"},"schema_version":"1.0"},"canonical_sha256":"3f717c58add43b00dddfd9bffc098673f2dd0f01c029fde8b0eb37ac49f15cf6","source":{"kind":"arxiv","id":"2111.11743","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.11743","created_at":"2026-07-05T03:34:12Z"},{"alias_kind":"arxiv_version","alias_value":"2111.11743v1","created_at":"2026-07-05T03:34:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.11743","created_at":"2026-07-05T03:34:12Z"},{"alias_kind":"pith_short_12","alias_value":"H5YXYWFN2Q5Q","created_at":"2026-07-05T03:34:12Z"},{"alias_kind":"pith_short_16","alias_value":"H5YXYWFN2Q5QBXO7","created_at":"2026-07-05T03:34:12Z"},{"alias_kind":"pith_short_8","alias_value":"H5YXYWFN","created_at":"2026-07-05T03:34:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:H5YXYWFN2Q5QBXO73G77YCMGOP","target":"record","payload":{"canonical_record":{"source":{"id":"2111.11743","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2021-11-23T09:27:20Z","cross_cats_sorted":["cs.LG","math.DS"],"title_canon_sha256":"36e5f8027585d90eaff37127d4c037138ffaf8813a69b61f2dd4982e47aa0a6c","abstract_canon_sha256":"4f03a9a4db93fe32349b55f277520d93e7ad0fbad328b51551b09ae13cdaaef2"},"schema_version":"1.0"},"canonical_sha256":"3f717c58add43b00dddfd9bffc098673f2dd0f01c029fde8b0eb37ac49f15cf6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:34:12.345092Z","signature_b64":"LYOUJG3DDzpJjZvncqu8mbD05uJQLxYeure5+hZn31FXECoCFKXtToSWdcftDGxa+wWEwwrPKyVWE7CxxQqECA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f717c58add43b00dddfd9bffc098673f2dd0f01c029fde8b0eb37ac49f15cf6","last_reissued_at":"2026-07-05T03:34:12.344677Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:34:12.344677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.11743","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":"2026-07-05T03:34:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E3nVwJr88S+bA8UX4JNI6t2kI09lu0RC7cntmXDBIltFA84tu7nLrw/m8wX3VwYdfM+0BwYnxVySF/6ZQHaHAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:49:48.913675Z"},"content_sha256":"c6ad90f8fd6d0f9de51601baf8151e6fa2a77d1ee4e5b4173368c2a01bc25eaf","schema_version":"1.0","event_id":"sha256:c6ad90f8fd6d0f9de51601baf8151e6fa2a77d1ee4e5b4173368c2a01bc25eaf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:H5YXYWFN2Q5QBXO73G77YCMGOP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Independent Learning in Stochastic Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.DS"],"primary_cat":"cs.GT","authors_text":"Asuman Ozdaglar, Kaiqing Zhang, Muhammed O. Sayin","submitted_at":"2021-11-23T09:27:20Z","abstract_excerpt":"Reinforcement learning (RL) has recently achieved tremendous successes in many artificial intelligence applications. Many of the forefront applications of RL involve multiple agents, e.g., playing chess and Go games, autonomous driving, and robotics. Unfortunately, the framework upon which classical RL builds is inappropriate for multi-agent learning, as it assumes an agent's environment is stationary and does not take into account the adaptivity of other agents. In this review paper, we present the model of stochastic games for multi-agent learning in dynamic environments. We focus on the dev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.11743","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/2111.11743/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":"2026-07-05T03:34:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TkkDUvGQ1oWZ6a0FdOQFMq9iHhRP0oi/rTUaxrR4NQhczxWOP+rSjT3kp7aajdex9f/FC90YfSyzppbr5rr3Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:49:48.914193Z"},"content_sha256":"33a5c2cdd7e60c87461382af8bf2ab212fbf3d523988d57d2d1bdcbc1bc02946","schema_version":"1.0","event_id":"sha256:33a5c2cdd7e60c87461382af8bf2ab212fbf3d523988d57d2d1bdcbc1bc02946"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H5YXYWFN2Q5QBXO73G77YCMGOP/bundle.json","state_url":"https://pith.science/pith/H5YXYWFN2Q5QBXO73G77YCMGOP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H5YXYWFN2Q5QBXO73G77YCMGOP/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":"2026-08-08T19:49:48Z","links":{"resolver":"https://pith.science/pith/H5YXYWFN2Q5QBXO73G77YCMGOP","bundle":"https://pith.science/pith/H5YXYWFN2Q5QBXO73G77YCMGOP/bundle.json","state":"https://pith.science/pith/H5YXYWFN2Q5QBXO73G77YCMGOP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H5YXYWFN2Q5QBXO73G77YCMGOP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:H5YXYWFN2Q5QBXO73G77YCMGOP","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":"4f03a9a4db93fe32349b55f277520d93e7ad0fbad328b51551b09ae13cdaaef2","cross_cats_sorted":["cs.LG","math.DS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2021-11-23T09:27:20Z","title_canon_sha256":"36e5f8027585d90eaff37127d4c037138ffaf8813a69b61f2dd4982e47aa0a6c"},"schema_version":"1.0","source":{"id":"2111.11743","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.11743","created_at":"2026-07-05T03:34:12Z"},{"alias_kind":"arxiv_version","alias_value":"2111.11743v1","created_at":"2026-07-05T03:34:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.11743","created_at":"2026-07-05T03:34:12Z"},{"alias_kind":"pith_short_12","alias_value":"H5YXYWFN2Q5Q","created_at":"2026-07-05T03:34:12Z"},{"alias_kind":"pith_short_16","alias_value":"H5YXYWFN2Q5QBXO7","created_at":"2026-07-05T03:34:12Z"},{"alias_kind":"pith_short_8","alias_value":"H5YXYWFN","created_at":"2026-07-05T03:34:12Z"}],"graph_snapshots":[{"event_id":"sha256:33a5c2cdd7e60c87461382af8bf2ab212fbf3d523988d57d2d1bdcbc1bc02946","target":"graph","created_at":"2026-07-05T03:34:12Z","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/2111.11743/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has recently achieved tremendous successes in many artificial intelligence applications. Many of the forefront applications of RL involve multiple agents, e.g., playing chess and Go games, autonomous driving, and robotics. Unfortunately, the framework upon which classical RL builds is inappropriate for multi-agent learning, as it assumes an agent's environment is stationary and does not take into account the adaptivity of other agents. In this review paper, we present the model of stochastic games for multi-agent learning in dynamic environments. We focus on the dev","authors_text":"Asuman Ozdaglar, Kaiqing Zhang, Muhammed O. Sayin","cross_cats":["cs.LG","math.DS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2021-11-23T09:27:20Z","title":"Independent Learning in Stochastic Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.11743","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:c6ad90f8fd6d0f9de51601baf8151e6fa2a77d1ee4e5b4173368c2a01bc25eaf","target":"record","created_at":"2026-07-05T03:34:12Z","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":"4f03a9a4db93fe32349b55f277520d93e7ad0fbad328b51551b09ae13cdaaef2","cross_cats_sorted":["cs.LG","math.DS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2021-11-23T09:27:20Z","title_canon_sha256":"36e5f8027585d90eaff37127d4c037138ffaf8813a69b61f2dd4982e47aa0a6c"},"schema_version":"1.0","source":{"id":"2111.11743","kind":"arxiv","version":1}},"canonical_sha256":"3f717c58add43b00dddfd9bffc098673f2dd0f01c029fde8b0eb37ac49f15cf6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f717c58add43b00dddfd9bffc098673f2dd0f01c029fde8b0eb37ac49f15cf6","first_computed_at":"2026-07-05T03:34:12.344677Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:34:12.344677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LYOUJG3DDzpJjZvncqu8mbD05uJQLxYeure5+hZn31FXECoCFKXtToSWdcftDGxa+wWEwwrPKyVWE7CxxQqECA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:34:12.345092Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.11743","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6ad90f8fd6d0f9de51601baf8151e6fa2a77d1ee4e5b4173368c2a01bc25eaf","sha256:33a5c2cdd7e60c87461382af8bf2ab212fbf3d523988d57d2d1bdcbc1bc02946"],"state_sha256":"01c22489c9e88e7909e8815f5d13e55df649d46faee1e0edbfc76448599b6702"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G2USTdhBrnriBC4xc4pgpTRcmBW4ZyRxJJtdfaAJ5sGwzU4DV6ZDA08NcsgVGL5IA7sS9PKdzKQcB25xbkjoAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:49:48.918292Z","bundle_sha256":"b831d1ec7b857809ba69a6c12d2094af24a3624fa35afc3d9deb8b303aa91fa0"}}