{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:FSD2ZS3VOVUITZVX3FYDLMHLHK","short_pith_number":"pith:FSD2ZS3V","canonical_record":{"source":{"id":"1807.09936","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-26T03:21:49Z","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"title_canon_sha256":"fad9615a91bd3fdc59a73a8f28434b74fa3c879c42d35a63346e5442e5b07cd6","abstract_canon_sha256":"fc649da372826e5bda697c216750c93ef87c5b8dbf4de318194db300dcec4cfc"},"schema_version":"1.0"},"canonical_sha256":"2c87accb75756889e6b7d97035b0eb3ab5ce2e54261d51ed2cce60aa77f31478","source":{"kind":"arxiv","id":"1807.09936","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.09936","created_at":"2026-05-18T00:09:46Z"},{"alias_kind":"arxiv_version","alias_value":"1807.09936v1","created_at":"2026-05-18T00:09:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.09936","created_at":"2026-05-18T00:09:46Z"},{"alias_kind":"pith_short_12","alias_value":"FSD2ZS3VOVUI","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"FSD2ZS3VOVUITZVX","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"FSD2ZS3V","created_at":"2026-05-18T12:32:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:FSD2ZS3VOVUITZVX3FYDLMHLHK","target":"record","payload":{"canonical_record":{"source":{"id":"1807.09936","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-26T03:21:49Z","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"title_canon_sha256":"fad9615a91bd3fdc59a73a8f28434b74fa3c879c42d35a63346e5442e5b07cd6","abstract_canon_sha256":"fc649da372826e5bda697c216750c93ef87c5b8dbf4de318194db300dcec4cfc"},"schema_version":"1.0"},"canonical_sha256":"2c87accb75756889e6b7d97035b0eb3ab5ce2e54261d51ed2cce60aa77f31478","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:46.027840Z","signature_b64":"LaSC8aQkGSIX6R8U9FjGwXZWixDUzAM2QZG6hL8qA+KCG0r7tOVCfKjWETKNXQWrAQ9qlysBWCm+SsB4v+yKBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c87accb75756889e6b7d97035b0eb3ab5ce2e54261d51ed2cce60aa77f31478","last_reissued_at":"2026-05-18T00:09:46.027094Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:46.027094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.09936","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":"2026-05-18T00:09:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vZcV4nC4Z5veNKLnEsZp9Gw0PGnVuJqmW/xNWgTuWdVdu5R2gj5uIj7rHDOOlZlma/D9zYpJDoyM8PggmrsHCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T18:07:04.456482Z"},"content_sha256":"52450ee792f85d897702bec35cc651a89987a6d2ab09e58a83003784f48432de","schema_version":"1.0","event_id":"sha256:52450ee792f85d897702bec35cc651a89987a6d2ab09e58a83003784f48432de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:FSD2ZS3VOVUITZVX3FYDLMHLHK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Agent Generative Adversarial Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dorsa Sadigh, Hongyu Ren, Jiaming Song, Stefano Ermon","submitted_at":"2018-07-26T03:21:49Z","abstract_excerpt":"Imitation learning algorithms can be used to learn a policy from expert demonstrations without access to a reward signal. However, most existing approaches are not applicable in multi-agent settings due to the existence of multiple (Nash) equilibria and non-stationary environments. We propose a new framework for multi-agent imitation learning for general Markov games, where we build upon a generalized notion of inverse reinforcement learning. We further introduce a practical multi-agent actor-critic algorithm with good empirical performance. Our method can be used to imitate complex behaviors "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.09936","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":"2026-05-18T00:09:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/dVIT9eH1YggUu+qKifE+9zpodbvVH+kcsVLz0EiWWwhe+sOr6cWt5QDcNl0LIqk1dtOt90mDQB2EK39pLPrAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T18:07:04.457142Z"},"content_sha256":"9d82847c684e15e54bc9bb6a41fa6b4c028e0377e63a03b8668f5b25088aa260","schema_version":"1.0","event_id":"sha256:9d82847c684e15e54bc9bb6a41fa6b4c028e0377e63a03b8668f5b25088aa260"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FSD2ZS3VOVUITZVX3FYDLMHLHK/bundle.json","state_url":"https://pith.science/pith/FSD2ZS3VOVUITZVX3FYDLMHLHK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FSD2ZS3VOVUITZVX3FYDLMHLHK/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":"2026-05-29T18:07:04Z","links":{"resolver":"https://pith.science/pith/FSD2ZS3VOVUITZVX3FYDLMHLHK","bundle":"https://pith.science/pith/FSD2ZS3VOVUITZVX3FYDLMHLHK/bundle.json","state":"https://pith.science/pith/FSD2ZS3VOVUITZVX3FYDLMHLHK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FSD2ZS3VOVUITZVX3FYDLMHLHK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:FSD2ZS3VOVUITZVX3FYDLMHLHK","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":"fc649da372826e5bda697c216750c93ef87c5b8dbf4de318194db300dcec4cfc","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-26T03:21:49Z","title_canon_sha256":"fad9615a91bd3fdc59a73a8f28434b74fa3c879c42d35a63346e5442e5b07cd6"},"schema_version":"1.0","source":{"id":"1807.09936","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.09936","created_at":"2026-05-18T00:09:46Z"},{"alias_kind":"arxiv_version","alias_value":"1807.09936v1","created_at":"2026-05-18T00:09:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.09936","created_at":"2026-05-18T00:09:46Z"},{"alias_kind":"pith_short_12","alias_value":"FSD2ZS3VOVUI","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"FSD2ZS3VOVUITZVX","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"FSD2ZS3V","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:9d82847c684e15e54bc9bb6a41fa6b4c028e0377e63a03b8668f5b25088aa260","target":"graph","created_at":"2026-05-18T00:09:46Z","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":"Imitation learning algorithms can be used to learn a policy from expert demonstrations without access to a reward signal. However, most existing approaches are not applicable in multi-agent settings due to the existence of multiple (Nash) equilibria and non-stationary environments. We propose a new framework for multi-agent imitation learning for general Markov games, where we build upon a generalized notion of inverse reinforcement learning. We further introduce a practical multi-agent actor-critic algorithm with good empirical performance. Our method can be used to imitate complex behaviors ","authors_text":"Dorsa Sadigh, Hongyu Ren, Jiaming Song, Stefano Ermon","cross_cats":["cs.AI","cs.MA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-26T03:21:49Z","title":"Multi-Agent Generative Adversarial Imitation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.09936","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":"sha256:52450ee792f85d897702bec35cc651a89987a6d2ab09e58a83003784f48432de","target":"record","created_at":"2026-05-18T00:09:46Z","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":"fc649da372826e5bda697c216750c93ef87c5b8dbf4de318194db300dcec4cfc","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-26T03:21:49Z","title_canon_sha256":"fad9615a91bd3fdc59a73a8f28434b74fa3c879c42d35a63346e5442e5b07cd6"},"schema_version":"1.0","source":{"id":"1807.09936","kind":"arxiv","version":1}},"canonical_sha256":"2c87accb75756889e6b7d97035b0eb3ab5ce2e54261d51ed2cce60aa77f31478","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c87accb75756889e6b7d97035b0eb3ab5ce2e54261d51ed2cce60aa77f31478","first_computed_at":"2026-05-18T00:09:46.027094Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:09:46.027094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LaSC8aQkGSIX6R8U9FjGwXZWixDUzAM2QZG6hL8qA+KCG0r7tOVCfKjWETKNXQWrAQ9qlysBWCm+SsB4v+yKBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:09:46.027840Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.09936","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52450ee792f85d897702bec35cc651a89987a6d2ab09e58a83003784f48432de","sha256:9d82847c684e15e54bc9bb6a41fa6b4c028e0377e63a03b8668f5b25088aa260"],"state_sha256":"cdcdb48f3bb18c3d2d484d1ee0b4023d3c4f4585bf78139b4446e54182f66529"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DAiNk3Eg6yWebFTDHRS3QUeHLLAdafI7XFZMhUnaKCiZLdhu08Q2wxNuGmvFMR6sL4M164p212N3vgNEVO7uBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T18:07:04.460679Z","bundle_sha256":"c84fd7d987e6093488c79c2dad88aa73366428d055728792778646884a5c2064"}}