{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:6RD3BRGAJC32OPMG4HRT2DWHXO","short_pith_number":"pith:6RD3BRGA","canonical_record":{"source":{"id":"1706.02275","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-07T17:35:00Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"2d1b31e467eb321e40fda851ae1cdbe502d1479d44063a8b3a828f29056383b0","abstract_canon_sha256":"49df20f1ca08e203c94b018a35f73d224e0dc66d9dc0a6ccc085f2e41947b128"},"schema_version":"1.0"},"canonical_sha256":"f447b0c4c048b7a73d86e1e33d0ec7bb95d3b1f01dd5ad9bbf1f462ff3c470a6","source":{"kind":"arxiv","id":"1706.02275","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.02275","created_at":"2026-07-05T00:47:54Z"},{"alias_kind":"arxiv_version","alias_value":"1706.02275v4","created_at":"2026-07-05T00:47:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.02275","created_at":"2026-07-05T00:47:54Z"},{"alias_kind":"pith_short_12","alias_value":"6RD3BRGAJC32","created_at":"2026-07-05T00:47:54Z"},{"alias_kind":"pith_short_16","alias_value":"6RD3BRGAJC32OPMG","created_at":"2026-07-05T00:47:54Z"},{"alias_kind":"pith_short_8","alias_value":"6RD3BRGA","created_at":"2026-07-05T00:47:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:6RD3BRGAJC32OPMG4HRT2DWHXO","target":"record","payload":{"canonical_record":{"source":{"id":"1706.02275","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-07T17:35:00Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"2d1b31e467eb321e40fda851ae1cdbe502d1479d44063a8b3a828f29056383b0","abstract_canon_sha256":"49df20f1ca08e203c94b018a35f73d224e0dc66d9dc0a6ccc085f2e41947b128"},"schema_version":"1.0"},"canonical_sha256":"f447b0c4c048b7a73d86e1e33d0ec7bb95d3b1f01dd5ad9bbf1f462ff3c470a6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:47:54.258244Z","signature_b64":"20RP/3pwK4XH0DdLXVJVfIaKiZ7YknxN1lpBz0QFFF9Qiq1G1ybHwpA38BW0kXJqNY4y5dsVKtVaFa9sFg6yCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f447b0c4c048b7a73d86e1e33d0ec7bb95d3b1f01dd5ad9bbf1f462ff3c470a6","last_reissued_at":"2026-07-05T00:47:54.257769Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:47:54.257769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.02275","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:47:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fV3caOfYdoKX62f0rlMZaMTzJl8RLx5NRb7tubvlcd25ekFqaVkY59xyq9BGdPwA7omOACArxwhTyIfa3elRBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T15:49:11.467121Z"},"content_sha256":"a8f7ac9e276277daf7d86c436a72cc2f17b677a78d3e3d45c3fcc548e8222661","schema_version":"1.0","event_id":"sha256:a8f7ac9e276277daf7d86c436a72cc2f17b677a78d3e3d45c3fcc548e8222661"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:6RD3BRGAJC32OPMG4HRT2DWHXO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Aviv Tamar, Igor Mordatch, Jean Harb, Pieter Abbeel, Ryan Lowe, Yi Wu","submitted_at":"2017-06-07T17:35:00Z","abstract_excerpt":"We explore deep reinforcement learning methods for multi-agent domains. We begin by analyzing the difficulty of traditional algorithms in the multi-agent case: Q-learning is challenged by an inherent non-stationarity of the environment, while policy gradient suffers from a variance that increases as the number of agents grows. We then present an adaptation of actor-critic methods that considers action policies of other agents and is able to successfully learn policies that require complex multi-agent coordination. Additionally, we introduce a training regimen utilizing an ensemble of policies "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.02275","kind":"arxiv","version":4},"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/1706.02275/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":"2026-07-05T00:47:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eS35d7saNkJIyIp8r8Tr1eBWc1ztgkFEOWYdabsWRrb05nXg3zal64X/TNlvgMhi5o8ROXRHGrGzdjY7cVDjDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T15:49:11.467676Z"},"content_sha256":"bcd09ed715213ef72059741c75710f02ce887c272907f55a440ab89925c267ba","schema_version":"1.0","event_id":"sha256:bcd09ed715213ef72059741c75710f02ce887c272907f55a440ab89925c267ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6RD3BRGAJC32OPMG4HRT2DWHXO/bundle.json","state_url":"https://pith.science/pith/6RD3BRGAJC32OPMG4HRT2DWHXO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6RD3BRGAJC32OPMG4HRT2DWHXO/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":"2026-08-06T15:49:11Z","links":{"resolver":"https://pith.science/pith/6RD3BRGAJC32OPMG4HRT2DWHXO","bundle":"https://pith.science/pith/6RD3BRGAJC32OPMG4HRT2DWHXO/bundle.json","state":"https://pith.science/pith/6RD3BRGAJC32OPMG4HRT2DWHXO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6RD3BRGAJC32OPMG4HRT2DWHXO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:6RD3BRGAJC32OPMG4HRT2DWHXO","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":"49df20f1ca08e203c94b018a35f73d224e0dc66d9dc0a6ccc085f2e41947b128","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-07T17:35:00Z","title_canon_sha256":"2d1b31e467eb321e40fda851ae1cdbe502d1479d44063a8b3a828f29056383b0"},"schema_version":"1.0","source":{"id":"1706.02275","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.02275","created_at":"2026-07-05T00:47:54Z"},{"alias_kind":"arxiv_version","alias_value":"1706.02275v4","created_at":"2026-07-05T00:47:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.02275","created_at":"2026-07-05T00:47:54Z"},{"alias_kind":"pith_short_12","alias_value":"6RD3BRGAJC32","created_at":"2026-07-05T00:47:54Z"},{"alias_kind":"pith_short_16","alias_value":"6RD3BRGAJC32OPMG","created_at":"2026-07-05T00:47:54Z"},{"alias_kind":"pith_short_8","alias_value":"6RD3BRGA","created_at":"2026-07-05T00:47:54Z"}],"graph_snapshots":[{"event_id":"sha256:bcd09ed715213ef72059741c75710f02ce887c272907f55a440ab89925c267ba","target":"graph","created_at":"2026-07-05T00:47:54Z","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/1706.02275/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We explore deep reinforcement learning methods for multi-agent domains. We begin by analyzing the difficulty of traditional algorithms in the multi-agent case: Q-learning is challenged by an inherent non-stationarity of the environment, while policy gradient suffers from a variance that increases as the number of agents grows. We then present an adaptation of actor-critic methods that considers action policies of other agents and is able to successfully learn policies that require complex multi-agent coordination. Additionally, we introduce a training regimen utilizing an ensemble of policies ","authors_text":"Aviv Tamar, Igor Mordatch, Jean Harb, Pieter Abbeel, Ryan Lowe, Yi Wu","cross_cats":["cs.AI","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-07T17:35:00Z","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.02275","kind":"arxiv","version":4},"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:a8f7ac9e276277daf7d86c436a72cc2f17b677a78d3e3d45c3fcc548e8222661","target":"record","created_at":"2026-07-05T00:47:54Z","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":"49df20f1ca08e203c94b018a35f73d224e0dc66d9dc0a6ccc085f2e41947b128","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-07T17:35:00Z","title_canon_sha256":"2d1b31e467eb321e40fda851ae1cdbe502d1479d44063a8b3a828f29056383b0"},"schema_version":"1.0","source":{"id":"1706.02275","kind":"arxiv","version":4}},"canonical_sha256":"f447b0c4c048b7a73d86e1e33d0ec7bb95d3b1f01dd5ad9bbf1f462ff3c470a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f447b0c4c048b7a73d86e1e33d0ec7bb95d3b1f01dd5ad9bbf1f462ff3c470a6","first_computed_at":"2026-07-05T00:47:54.257769Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:47:54.257769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"20RP/3pwK4XH0DdLXVJVfIaKiZ7YknxN1lpBz0QFFF9Qiq1G1ybHwpA38BW0kXJqNY4y5dsVKtVaFa9sFg6yCw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:47:54.258244Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.02275","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8f7ac9e276277daf7d86c436a72cc2f17b677a78d3e3d45c3fcc548e8222661","sha256:bcd09ed715213ef72059741c75710f02ce887c272907f55a440ab89925c267ba"],"state_sha256":"dbc54a97ddb655011415453caf85555dab42fd93682de20bea468117c88500ce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aJY4qqI/Tk6RF3BS3woKF/klUWDDW55huG0wToXzaIWqypBSs+/eyEkJWalsnlhEjOT2aQ4OqpiMvvul5DY/CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T15:49:11.471505Z","bundle_sha256":"5a04f952d267be083a4ba42c92cc3556c51de89d99419d4868a2008d4094f94b"}}