{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:7P2HD4LJJ2PENE3I2TSPXYWSY5","short_pith_number":"pith:7P2HD4LJ","canonical_record":{"source":{"id":"2009.14180","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-09-29T17:48:10Z","cross_cats_sorted":[],"title_canon_sha256":"4fe84b84277b9a70d21ca7d02c0004e698c60b45d6e2b8690278795c0ed1e604","abstract_canon_sha256":"497493c53dd95caa04bb434005c21aeab7117150ef4390302c9361a8bb105df3"},"schema_version":"1.0"},"canonical_sha256":"fbf471f1694e9e469368d4e4fbe2d2c751bdf4b74c2a59c642fa72d971ad1132","source":{"kind":"arxiv","id":"2009.14180","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.14180","created_at":"2026-07-05T02:46:00Z"},{"alias_kind":"arxiv_version","alias_value":"2009.14180v2","created_at":"2026-07-05T02:46:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.14180","created_at":"2026-07-05T02:46:00Z"},{"alias_kind":"pith_short_12","alias_value":"7P2HD4LJJ2PE","created_at":"2026-07-05T02:46:00Z"},{"alias_kind":"pith_short_16","alias_value":"7P2HD4LJJ2PENE3I","created_at":"2026-07-05T02:46:00Z"},{"alias_kind":"pith_short_8","alias_value":"7P2HD4LJ","created_at":"2026-07-05T02:46:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:7P2HD4LJJ2PENE3I2TSPXYWSY5","target":"record","payload":{"canonical_record":{"source":{"id":"2009.14180","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-09-29T17:48:10Z","cross_cats_sorted":[],"title_canon_sha256":"4fe84b84277b9a70d21ca7d02c0004e698c60b45d6e2b8690278795c0ed1e604","abstract_canon_sha256":"497493c53dd95caa04bb434005c21aeab7117150ef4390302c9361a8bb105df3"},"schema_version":"1.0"},"canonical_sha256":"fbf471f1694e9e469368d4e4fbe2d2c751bdf4b74c2a59c642fa72d971ad1132","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:00.891854Z","signature_b64":"5FVoDXwhOmqUMkC3f+S1Pk3xvUhD3J0vqOrvirjIa7Q6nuqfImIvz3o32rqHMVaxrd8WMaEpmqSlkhsHnpQRCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbf471f1694e9e469368d4e4fbe2d2c751bdf4b74c2a59c642fa72d971ad1132","last_reissued_at":"2026-07-05T02:46:00.891416Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:00.891416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2009.14180","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":"2026-07-05T02:46:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q0xBDOPlKJk5stMd9ZDiIffgOD24IivIvKUPWpLBCVDABRumjo5sf3tmB/iKUmekPype/47/Tuqy/p//GyLNBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T03:24:20.229088Z"},"content_sha256":"2246b17585a4824811a0e085279e30ce4aaaaac88b2842852f20f0da5c5b34b1","schema_version":"1.0","event_id":"sha256:2246b17585a4824811a0e085279e30ce4aaaaac88b2842852f20f0da5c5b34b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:7P2HD4LJJ2PENE3I2TSPXYWSY5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Play against Any Mixture of Opponents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Max Olan Smith, Michael P. Wellman, Thomas Anthony, Yongzhao Wang","submitted_at":"2020-09-29T17:48:10Z","abstract_excerpt":"Intuitively, experience playing against one mixture of opponents in a given domain should be relevant for a different mixture in the same domain. We propose a transfer learning method, Q-Mixing, that starts by learning Q-values against each pure-strategy opponent. Then a Q-value for any distribution of opponent strategies is approximated by appropriately averaging the separately learned Q-values. From these components, we construct policies against all opponent mixtures without any further training. We empirically validate Q-Mixing in two environments: a simple grid-world soccer environment, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.14180","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2009.14180/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":"2026-07-05T02:46:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Injp0Zsvj/LgQxjpsJjNX8kobn3GcUDQ5o6xsA8PaPNJHhxQy0ZyFhOl06WRz926wuXQ0Jl7vkA8rp3rfTS9Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T03:24:20.229610Z"},"content_sha256":"c1bcf285a19beb7809b1cee25d3621106acff82a104f2cfe74ffa8de9b843c4c","schema_version":"1.0","event_id":"sha256:c1bcf285a19beb7809b1cee25d3621106acff82a104f2cfe74ffa8de9b843c4c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7P2HD4LJJ2PENE3I2TSPXYWSY5/bundle.json","state_url":"https://pith.science/pith/7P2HD4LJJ2PENE3I2TSPXYWSY5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7P2HD4LJJ2PENE3I2TSPXYWSY5/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":"2026-08-19T03:24:20Z","links":{"resolver":"https://pith.science/pith/7P2HD4LJJ2PENE3I2TSPXYWSY5","bundle":"https://pith.science/pith/7P2HD4LJJ2PENE3I2TSPXYWSY5/bundle.json","state":"https://pith.science/pith/7P2HD4LJJ2PENE3I2TSPXYWSY5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7P2HD4LJJ2PENE3I2TSPXYWSY5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:7P2HD4LJJ2PENE3I2TSPXYWSY5","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":"497493c53dd95caa04bb434005c21aeab7117150ef4390302c9361a8bb105df3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-09-29T17:48:10Z","title_canon_sha256":"4fe84b84277b9a70d21ca7d02c0004e698c60b45d6e2b8690278795c0ed1e604"},"schema_version":"1.0","source":{"id":"2009.14180","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.14180","created_at":"2026-07-05T02:46:00Z"},{"alias_kind":"arxiv_version","alias_value":"2009.14180v2","created_at":"2026-07-05T02:46:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.14180","created_at":"2026-07-05T02:46:00Z"},{"alias_kind":"pith_short_12","alias_value":"7P2HD4LJJ2PE","created_at":"2026-07-05T02:46:00Z"},{"alias_kind":"pith_short_16","alias_value":"7P2HD4LJJ2PENE3I","created_at":"2026-07-05T02:46:00Z"},{"alias_kind":"pith_short_8","alias_value":"7P2HD4LJ","created_at":"2026-07-05T02:46:00Z"}],"graph_snapshots":[{"event_id":"sha256:c1bcf285a19beb7809b1cee25d3621106acff82a104f2cfe74ffa8de9b843c4c","target":"graph","created_at":"2026-07-05T02:46:00Z","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/2009.14180/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Intuitively, experience playing against one mixture of opponents in a given domain should be relevant for a different mixture in the same domain. We propose a transfer learning method, Q-Mixing, that starts by learning Q-values against each pure-strategy opponent. Then a Q-value for any distribution of opponent strategies is approximated by appropriately averaging the separately learned Q-values. From these components, we construct policies against all opponent mixtures without any further training. We empirically validate Q-Mixing in two environments: a simple grid-world soccer environment, a","authors_text":"Max Olan Smith, Michael P. Wellman, Thomas Anthony, Yongzhao Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-09-29T17:48:10Z","title":"Learning to Play against Any Mixture of Opponents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.14180","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":"sha256:2246b17585a4824811a0e085279e30ce4aaaaac88b2842852f20f0da5c5b34b1","target":"record","created_at":"2026-07-05T02:46:00Z","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":"497493c53dd95caa04bb434005c21aeab7117150ef4390302c9361a8bb105df3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-09-29T17:48:10Z","title_canon_sha256":"4fe84b84277b9a70d21ca7d02c0004e698c60b45d6e2b8690278795c0ed1e604"},"schema_version":"1.0","source":{"id":"2009.14180","kind":"arxiv","version":2}},"canonical_sha256":"fbf471f1694e9e469368d4e4fbe2d2c751bdf4b74c2a59c642fa72d971ad1132","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fbf471f1694e9e469368d4e4fbe2d2c751bdf4b74c2a59c642fa72d971ad1132","first_computed_at":"2026-07-05T02:46:00.891416Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:46:00.891416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5FVoDXwhOmqUMkC3f+S1Pk3xvUhD3J0vqOrvirjIa7Q6nuqfImIvz3o32rqHMVaxrd8WMaEpmqSlkhsHnpQRCw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:46:00.891854Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.14180","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2246b17585a4824811a0e085279e30ce4aaaaac88b2842852f20f0da5c5b34b1","sha256:c1bcf285a19beb7809b1cee25d3621106acff82a104f2cfe74ffa8de9b843c4c"],"state_sha256":"110dd25b92d45089b3b5c772b227b93e60c6aa797cc212f21dcf608fa6521815"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OZ3GAkfqQiudwHlzdJGo+T7S9v+5NT8gCig5d16+oSISe+6kzbt4axkbpiZltJc9L7PbUJ5YI2ic665vBxoOBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T03:24:20.234889Z","bundle_sha256":"2bf6712bd80bcd1ebfa372fdb852895c65ef2198e38e025186a17fb887fff476"}}