{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:XCWR7SELNEXTJJNS5WQ22KGIXZ","short_pith_number":"pith:XCWR7SEL","canonical_record":{"source":{"id":"1709.06656","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-19T21:41:51Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"13705088d4618b2b5a874377ac7811b8731e3e024e9827f61c4d981f3f3e85d9","abstract_canon_sha256":"989708cf19b90ae48e6de92ca1e14405de2b45c5c401f14df2d890f37d2e6bdd"},"schema_version":"1.0"},"canonical_sha256":"b8ad1fc88b692f34a5b2eda1ad28c8be7c1504e94459e88f9560947d196f4c8e","source":{"kind":"arxiv","id":"1709.06656","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.06656","created_at":"2026-05-17T23:44:48Z"},{"alias_kind":"arxiv_version","alias_value":"1709.06656v2","created_at":"2026-05-17T23:44:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.06656","created_at":"2026-05-17T23:44:48Z"},{"alias_kind":"pith_short_12","alias_value":"XCWR7SELNEXT","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"XCWR7SELNEXTJJNS","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"XCWR7SEL","created_at":"2026-05-18T12:31:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:XCWR7SELNEXTJJNS5WQ22KGIXZ","target":"record","payload":{"canonical_record":{"source":{"id":"1709.06656","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-19T21:41:51Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"13705088d4618b2b5a874377ac7811b8731e3e024e9827f61c4d981f3f3e85d9","abstract_canon_sha256":"989708cf19b90ae48e6de92ca1e14405de2b45c5c401f14df2d890f37d2e6bdd"},"schema_version":"1.0"},"canonical_sha256":"b8ad1fc88b692f34a5b2eda1ad28c8be7c1504e94459e88f9560947d196f4c8e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:48.512236Z","signature_b64":"zRPrHPNTDbu56bekZhQ62F1jFWKutxnuFMGgAJN+hpm2FKyJgkhCAnFDv7PzJLTwJBerXHC798XHaaYI2dy4Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8ad1fc88b692f34a5b2eda1ad28c8be7c1504e94459e88f9560947d196f4c8e","last_reissued_at":"2026-05-17T23:44:48.511676Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:48.511676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.06656","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":"2026-05-17T23:44:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w7Bgwq2IlfpHdcZsMvUEvHCaJ3UpPakXH/yuWyIVC82vi9bN1qVBjlhnQhTAaUbrsFXRFOc8SFyhS4Kbl+SSBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T20:50:47.531290Z"},"content_sha256":"4fdcecacbf6057ad1b361ef68a605e1c5099a1c8174e23f77994404f487f0b79","schema_version":"1.0","event_id":"sha256:4fdcecacbf6057ad1b361ef68a605e1c5099a1c8174e23f77994404f487f0b79"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:XCWR7SELNEXTJJNS5WQ22KGIXZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning for Event-Driven Multi-Agent Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Brendan D. Tracey, David Wolpert, James W. Bono, Justin Grana, Kunal Menda, Mykel J. Kochenderfer, Yi-Chun Chen","submitted_at":"2017-09-19T21:41:51Z","abstract_excerpt":"The incorporation of macro-actions (temporally extended actions) into multi-agent decision problems has the potential to address the curse of dimensionality associated with such decision problems. Since macro-actions last for stochastic durations, multiple agents executing decentralized policies in cooperative environments must act asynchronously. We present an algorithm that modifies generalized advantage estimation for temporally extended actions, allowing a state-of-the-art policy optimization algorithm to optimize policies in Dec-POMDPs in which agents act asynchronously. We show that our "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.06656","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":""},"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":"2026-05-17T23:44:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BeNeQQitCJNOMt0xgHps7cIiGLghiZ131xovcBRBPkStN0FBBntr7hlyT4KiH7rCSSD6Bqa1vzj6tH9g+E3SDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T20:50:47.531972Z"},"content_sha256":"c1b06748dd6ca9774fcaba8d88cf7f87c99c1a90568b36e46e6d911020f2f8ae","schema_version":"1.0","event_id":"sha256:c1b06748dd6ca9774fcaba8d88cf7f87c99c1a90568b36e46e6d911020f2f8ae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XCWR7SELNEXTJJNS5WQ22KGIXZ/bundle.json","state_url":"https://pith.science/pith/XCWR7SELNEXTJJNS5WQ22KGIXZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XCWR7SELNEXTJJNS5WQ22KGIXZ/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":"2026-05-31T20:50:47Z","links":{"resolver":"https://pith.science/pith/XCWR7SELNEXTJJNS5WQ22KGIXZ","bundle":"https://pith.science/pith/XCWR7SELNEXTJJNS5WQ22KGIXZ/bundle.json","state":"https://pith.science/pith/XCWR7SELNEXTJJNS5WQ22KGIXZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XCWR7SELNEXTJJNS5WQ22KGIXZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:XCWR7SELNEXTJJNS5WQ22KGIXZ","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":"989708cf19b90ae48e6de92ca1e14405de2b45c5c401f14df2d890f37d2e6bdd","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-19T21:41:51Z","title_canon_sha256":"13705088d4618b2b5a874377ac7811b8731e3e024e9827f61c4d981f3f3e85d9"},"schema_version":"1.0","source":{"id":"1709.06656","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.06656","created_at":"2026-05-17T23:44:48Z"},{"alias_kind":"arxiv_version","alias_value":"1709.06656v2","created_at":"2026-05-17T23:44:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.06656","created_at":"2026-05-17T23:44:48Z"},{"alias_kind":"pith_short_12","alias_value":"XCWR7SELNEXT","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"XCWR7SELNEXTJJNS","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"XCWR7SEL","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:c1b06748dd6ca9774fcaba8d88cf7f87c99c1a90568b36e46e6d911020f2f8ae","target":"graph","created_at":"2026-05-17T23:44:48Z","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":"The incorporation of macro-actions (temporally extended actions) into multi-agent decision problems has the potential to address the curse of dimensionality associated with such decision problems. Since macro-actions last for stochastic durations, multiple agents executing decentralized policies in cooperative environments must act asynchronously. We present an algorithm that modifies generalized advantage estimation for temporally extended actions, allowing a state-of-the-art policy optimization algorithm to optimize policies in Dec-POMDPs in which agents act asynchronously. We show that our ","authors_text":"Brendan D. Tracey, David Wolpert, James W. Bono, Justin Grana, Kunal Menda, Mykel J. Kochenderfer, Yi-Chun Chen","cross_cats":["cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-19T21:41:51Z","title":"Deep Reinforcement Learning for Event-Driven Multi-Agent Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.06656","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":"sha256:4fdcecacbf6057ad1b361ef68a605e1c5099a1c8174e23f77994404f487f0b79","target":"record","created_at":"2026-05-17T23:44:48Z","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":"989708cf19b90ae48e6de92ca1e14405de2b45c5c401f14df2d890f37d2e6bdd","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-19T21:41:51Z","title_canon_sha256":"13705088d4618b2b5a874377ac7811b8731e3e024e9827f61c4d981f3f3e85d9"},"schema_version":"1.0","source":{"id":"1709.06656","kind":"arxiv","version":2}},"canonical_sha256":"b8ad1fc88b692f34a5b2eda1ad28c8be7c1504e94459e88f9560947d196f4c8e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b8ad1fc88b692f34a5b2eda1ad28c8be7c1504e94459e88f9560947d196f4c8e","first_computed_at":"2026-05-17T23:44:48.511676Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:48.511676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zRPrHPNTDbu56bekZhQ62F1jFWKutxnuFMGgAJN+hpm2FKyJgkhCAnFDv7PzJLTwJBerXHC798XHaaYI2dy4Dw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:48.512236Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.06656","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fdcecacbf6057ad1b361ef68a605e1c5099a1c8174e23f77994404f487f0b79","sha256:c1b06748dd6ca9774fcaba8d88cf7f87c99c1a90568b36e46e6d911020f2f8ae"],"state_sha256":"b7d5e9db81b383823dfdd8b75e4934263946a8c3745ad9483a062b7c04de0e23"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"57KtHmTkTyaw4+ej8SuR+XJNI6VO0huGxqD7DSHbJj3CeCFtNbAElcu/qIR8vHVYxtzvPl/hDH+A29i22x07Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T20:50:47.535232Z","bundle_sha256":"9ff06d768cebf005d406a010092c7f5a547ceca4433bf5d9836fbe82f86b0010"}}