{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:AGMZ6PUPULMPXL5OSTSMWR5J3A","short_pith_number":"pith:AGMZ6PUP","canonical_record":{"source":{"id":"1709.04326","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-13T13:42:15Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"5f5ef6e35d7dd77643613be1d57f709273b1203ac5f06b15e631f5822337973d","abstract_canon_sha256":"e80d6be3effe879934f085a53058329f83d88c5d55b4d772897c571e75f8752a"},"schema_version":"1.0"},"canonical_sha256":"01999f3e8fa2d8fbafae94e4cb47a9d80de2200c19405e3adf097390f87f9684","source":{"kind":"arxiv","id":"1709.04326","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.04326","created_at":"2026-05-18T00:05:19Z"},{"alias_kind":"arxiv_version","alias_value":"1709.04326v4","created_at":"2026-05-18T00:05:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.04326","created_at":"2026-05-18T00:05:19Z"},{"alias_kind":"pith_short_12","alias_value":"AGMZ6PUPULMP","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"AGMZ6PUPULMPXL5O","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"AGMZ6PUP","created_at":"2026-05-18T12:31:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:AGMZ6PUPULMPXL5OSTSMWR5J3A","target":"record","payload":{"canonical_record":{"source":{"id":"1709.04326","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-13T13:42:15Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"5f5ef6e35d7dd77643613be1d57f709273b1203ac5f06b15e631f5822337973d","abstract_canon_sha256":"e80d6be3effe879934f085a53058329f83d88c5d55b4d772897c571e75f8752a"},"schema_version":"1.0"},"canonical_sha256":"01999f3e8fa2d8fbafae94e4cb47a9d80de2200c19405e3adf097390f87f9684","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:19.681300Z","signature_b64":"kdcRPs/rEGE5E8xCNY5+Pr27zI1yKdJE+zBHUBHfr43px0UZMO/qlutY3SdxZViKYMZqZkZ5tJrOgqbR33HZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01999f3e8fa2d8fbafae94e4cb47a9d80de2200c19405e3adf097390f87f9684","last_reissued_at":"2026-05-18T00:05:19.680654Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:19.680654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.04326","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":"2026-05-18T00:05:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qe66mPUbBs73NeHrWHMsm3qLT3/gnoHcuDb4jkPfhqjoOG1quxt7NchaOh9WoOnxdCPtV0PXN6FlBHmoxQQkDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:06:15.802780Z"},"content_sha256":"4c1931ab2890483fbcc6df48849b1a8ebdbad5a3ca2cdc33ddea5efade04c4be","schema_version":"1.0","event_id":"sha256:4c1931ab2890483fbcc6df48849b1a8ebdbad5a3ca2cdc33ddea5efade04c4be"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:AGMZ6PUPULMPXL5OSTSMWR5J3A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning with Opponent-Learning Awareness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.AI","authors_text":"Igor Mordatch, Jakob N. Foerster, Maruan Al-Shedivat, Pieter Abbeel, Richard Y. Chen, Shimon Whiteson","submitted_at":"2017-09-13T13:42:15Z","abstract_excerpt":"Multi-agent settings are quickly gathering importance in machine learning. This includes a plethora of recent work on deep multi-agent reinforcement learning, but also can be extended to hierarchical RL, generative adversarial networks and decentralised optimisation. In all these settings the presence of multiple learning agents renders the training problem non-stationary and often leads to unstable training or undesired final results. We present Learning with Opponent-Learning Awareness (LOLA), a method in which each agent shapes the anticipated learning of the other agents in the environment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.04326","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":""},"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":"2026-05-18T00:05:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rj5UM8PoBShVpi+G5w+nc8nequFP6/q/TXIyOx1fMkD9a3lTGaE3v3zJ6xNLRA+wY/FUyt7fNrBktONWlln1Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:06:15.803516Z"},"content_sha256":"a763ca3e030ae07df4b8e1502f853879beaa9483f7ff070ed3cf2fce5a68197b","schema_version":"1.0","event_id":"sha256:a763ca3e030ae07df4b8e1502f853879beaa9483f7ff070ed3cf2fce5a68197b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AGMZ6PUPULMPXL5OSTSMWR5J3A/bundle.json","state_url":"https://pith.science/pith/AGMZ6PUPULMPXL5OSTSMWR5J3A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AGMZ6PUPULMPXL5OSTSMWR5J3A/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":"2026-05-25T22:06:15Z","links":{"resolver":"https://pith.science/pith/AGMZ6PUPULMPXL5OSTSMWR5J3A","bundle":"https://pith.science/pith/AGMZ6PUPULMPXL5OSTSMWR5J3A/bundle.json","state":"https://pith.science/pith/AGMZ6PUPULMPXL5OSTSMWR5J3A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AGMZ6PUPULMPXL5OSTSMWR5J3A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:AGMZ6PUPULMPXL5OSTSMWR5J3A","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":"e80d6be3effe879934f085a53058329f83d88c5d55b4d772897c571e75f8752a","cross_cats_sorted":["cs.GT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-13T13:42:15Z","title_canon_sha256":"5f5ef6e35d7dd77643613be1d57f709273b1203ac5f06b15e631f5822337973d"},"schema_version":"1.0","source":{"id":"1709.04326","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.04326","created_at":"2026-05-18T00:05:19Z"},{"alias_kind":"arxiv_version","alias_value":"1709.04326v4","created_at":"2026-05-18T00:05:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.04326","created_at":"2026-05-18T00:05:19Z"},{"alias_kind":"pith_short_12","alias_value":"AGMZ6PUPULMP","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"AGMZ6PUPULMPXL5O","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"AGMZ6PUP","created_at":"2026-05-18T12:31:05Z"}],"graph_snapshots":[{"event_id":"sha256:a763ca3e030ae07df4b8e1502f853879beaa9483f7ff070ed3cf2fce5a68197b","target":"graph","created_at":"2026-05-18T00:05:19Z","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":"Multi-agent settings are quickly gathering importance in machine learning. This includes a plethora of recent work on deep multi-agent reinforcement learning, but also can be extended to hierarchical RL, generative adversarial networks and decentralised optimisation. In all these settings the presence of multiple learning agents renders the training problem non-stationary and often leads to unstable training or undesired final results. We present Learning with Opponent-Learning Awareness (LOLA), a method in which each agent shapes the anticipated learning of the other agents in the environment","authors_text":"Igor Mordatch, Jakob N. Foerster, Maruan Al-Shedivat, Pieter Abbeel, Richard Y. Chen, Shimon Whiteson","cross_cats":["cs.GT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-13T13:42:15Z","title":"Learning with Opponent-Learning Awareness"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.04326","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":"sha256:4c1931ab2890483fbcc6df48849b1a8ebdbad5a3ca2cdc33ddea5efade04c4be","target":"record","created_at":"2026-05-18T00:05:19Z","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":"e80d6be3effe879934f085a53058329f83d88c5d55b4d772897c571e75f8752a","cross_cats_sorted":["cs.GT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-13T13:42:15Z","title_canon_sha256":"5f5ef6e35d7dd77643613be1d57f709273b1203ac5f06b15e631f5822337973d"},"schema_version":"1.0","source":{"id":"1709.04326","kind":"arxiv","version":4}},"canonical_sha256":"01999f3e8fa2d8fbafae94e4cb47a9d80de2200c19405e3adf097390f87f9684","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01999f3e8fa2d8fbafae94e4cb47a9d80de2200c19405e3adf097390f87f9684","first_computed_at":"2026-05-18T00:05:19.680654Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:05:19.680654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kdcRPs/rEGE5E8xCNY5+Pr27zI1yKdJE+zBHUBHfr43px0UZMO/qlutY3SdxZViKYMZqZkZ5tJrOgqbR33HZDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:05:19.681300Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.04326","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c1931ab2890483fbcc6df48849b1a8ebdbad5a3ca2cdc33ddea5efade04c4be","sha256:a763ca3e030ae07df4b8e1502f853879beaa9483f7ff070ed3cf2fce5a68197b"],"state_sha256":"8626f62993e447b2804537ee5800bc95ff9b2b8828a0f5f7d23f0f72b71be912"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mw/tiqSU7s2Rh1oh0BViyFKRfD5EfTx/M8O4u+VSmhzvBjG7fNEchBPSnnzOhz3KygEtyG6Lzyt4BF/nki+ZDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T22:06:15.807197Z","bundle_sha256":"a48d9c313db140866b5de6223a11a9ec6a37ecb744b8f0df4198ff2d50bbd3ae"}}