{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:XZD7AJ4EYFFGBIEBGHIMB5R7R2","short_pith_number":"pith:XZD7AJ4E","canonical_record":{"source":{"id":"1908.01022","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-02T19:20:29Z","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"title_canon_sha256":"fab343dcf9c79dfbd58dea6c8b844dd7e2e4cfa900867b1e3632f5804bf4d5e3","abstract_canon_sha256":"14e67f7099552f7866df6563f791231f7f226d927eb2f7ed3bfbc942a5e5d34b"},"schema_version":"1.0"},"canonical_sha256":"be47f02784c14a60a08131d0c0f63f8e96719dc67b382130fd71359e410633b8","source":{"kind":"arxiv","id":"1908.01022","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.01022","created_at":"2026-07-05T02:04:25Z"},{"alias_kind":"arxiv_version","alias_value":"1908.01022v4","created_at":"2026-07-05T02:04:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.01022","created_at":"2026-07-05T02:04:25Z"},{"alias_kind":"pith_short_12","alias_value":"XZD7AJ4EYFFG","created_at":"2026-07-05T02:04:25Z"},{"alias_kind":"pith_short_16","alias_value":"XZD7AJ4EYFFGBIEB","created_at":"2026-07-05T02:04:25Z"},{"alias_kind":"pith_short_8","alias_value":"XZD7AJ4E","created_at":"2026-07-05T02:04:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:XZD7AJ4EYFFGBIEBGHIMB5R7R2","target":"record","payload":{"canonical_record":{"source":{"id":"1908.01022","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-02T19:20:29Z","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"title_canon_sha256":"fab343dcf9c79dfbd58dea6c8b844dd7e2e4cfa900867b1e3632f5804bf4d5e3","abstract_canon_sha256":"14e67f7099552f7866df6563f791231f7f226d927eb2f7ed3bfbc942a5e5d34b"},"schema_version":"1.0"},"canonical_sha256":"be47f02784c14a60a08131d0c0f63f8e96719dc67b382130fd71359e410633b8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:04:26.000012Z","signature_b64":"zwqh4pz9ublWGXH6boWYji8uQf0ct/ISIu7255+gDk0vLQzgaSKTPwys3/xmCuaD6wuiAcZqx6xio/UN6KdkBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be47f02784c14a60a08131d0c0f63f8e96719dc67b382130fd71359e410633b8","last_reissued_at":"2026-07-05T02:04:25.999605Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:04:25.999605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.01022","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":"2026-07-05T02:04:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uHUWXx6mIMCVibx5gkvQZ3of14eYxnNz86TzJ1W8EfwzI8u2zyzZ22PkSDRnMbeNV7HJLaKr5E0PZK1xk0bDCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T13:18:38.206418Z"},"content_sha256":"be152fc6196897b1e1f4c736b60f9f372b481a3d3f65965ca55d94cd9ace90a2","schema_version":"1.0","event_id":"sha256:be152fc6196897b1e1f4c736b60f9f372b481a3d3f65965ca55d94cd9ace90a2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:XZD7AJ4EYFFGBIEBGHIMB5R7R2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Health-Informed Policy Gradients for Multi-Agent Reinforcement 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":"Jaime Pena, Javona White Bear, Jayesh K. Gupta, Mykel J. Kochenderfer, Ross E. Allen, Yutai Zhou","submitted_at":"2019-08-02T19:20:29Z","abstract_excerpt":"This paper proposes a definition of system health in the context of multiple agents optimizing a joint reward function. We use this definition as a credit assignment term in a policy gradient algorithm to distinguish the contributions of individual agents to the global reward. The health-informed credit assignment is then extended to a multi-agent variant of the proximal policy optimization algorithm and demonstrated on particle and multiwalker robot environments that have characteristics such as system health, risk-taking, semi-expendable agents, continuous action spaces, and partial observab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.01022","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/1908.01022/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":"2026-07-05T02:04:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6XGG0noQPqszfPL1O9X2Q1Ps4nK1Ke9fOOAE6bbxnQ/U8Dk8TrTc+H1EmFT0pH8pNzFfXjJXRNQwfoQixwtdCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T13:18:38.206935Z"},"content_sha256":"19ecebe517122f2c1510a6691b1171a58dd7ab629b98beb4d4282e77ed8366ac","schema_version":"1.0","event_id":"sha256:19ecebe517122f2c1510a6691b1171a58dd7ab629b98beb4d4282e77ed8366ac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XZD7AJ4EYFFGBIEBGHIMB5R7R2/bundle.json","state_url":"https://pith.science/pith/XZD7AJ4EYFFGBIEBGHIMB5R7R2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XZD7AJ4EYFFGBIEBGHIMB5R7R2/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":"2026-08-16T13:18:38Z","links":{"resolver":"https://pith.science/pith/XZD7AJ4EYFFGBIEBGHIMB5R7R2","bundle":"https://pith.science/pith/XZD7AJ4EYFFGBIEBGHIMB5R7R2/bundle.json","state":"https://pith.science/pith/XZD7AJ4EYFFGBIEBGHIMB5R7R2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XZD7AJ4EYFFGBIEBGHIMB5R7R2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:XZD7AJ4EYFFGBIEBGHIMB5R7R2","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":"14e67f7099552f7866df6563f791231f7f226d927eb2f7ed3bfbc942a5e5d34b","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-02T19:20:29Z","title_canon_sha256":"fab343dcf9c79dfbd58dea6c8b844dd7e2e4cfa900867b1e3632f5804bf4d5e3"},"schema_version":"1.0","source":{"id":"1908.01022","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.01022","created_at":"2026-07-05T02:04:25Z"},{"alias_kind":"arxiv_version","alias_value":"1908.01022v4","created_at":"2026-07-05T02:04:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.01022","created_at":"2026-07-05T02:04:25Z"},{"alias_kind":"pith_short_12","alias_value":"XZD7AJ4EYFFG","created_at":"2026-07-05T02:04:25Z"},{"alias_kind":"pith_short_16","alias_value":"XZD7AJ4EYFFGBIEB","created_at":"2026-07-05T02:04:25Z"},{"alias_kind":"pith_short_8","alias_value":"XZD7AJ4E","created_at":"2026-07-05T02:04:25Z"}],"graph_snapshots":[{"event_id":"sha256:19ecebe517122f2c1510a6691b1171a58dd7ab629b98beb4d4282e77ed8366ac","target":"graph","created_at":"2026-07-05T02:04:25Z","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/1908.01022/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper proposes a definition of system health in the context of multiple agents optimizing a joint reward function. We use this definition as a credit assignment term in a policy gradient algorithm to distinguish the contributions of individual agents to the global reward. The health-informed credit assignment is then extended to a multi-agent variant of the proximal policy optimization algorithm and demonstrated on particle and multiwalker robot environments that have characteristics such as system health, risk-taking, semi-expendable agents, continuous action spaces, and partial observab","authors_text":"Jaime Pena, Javona White Bear, Jayesh K. Gupta, Mykel J. Kochenderfer, Ross E. Allen, Yutai Zhou","cross_cats":["cs.AI","cs.MA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-02T19:20:29Z","title":"Health-Informed Policy Gradients for Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.01022","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:be152fc6196897b1e1f4c736b60f9f372b481a3d3f65965ca55d94cd9ace90a2","target":"record","created_at":"2026-07-05T02:04:25Z","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":"14e67f7099552f7866df6563f791231f7f226d927eb2f7ed3bfbc942a5e5d34b","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-02T19:20:29Z","title_canon_sha256":"fab343dcf9c79dfbd58dea6c8b844dd7e2e4cfa900867b1e3632f5804bf4d5e3"},"schema_version":"1.0","source":{"id":"1908.01022","kind":"arxiv","version":4}},"canonical_sha256":"be47f02784c14a60a08131d0c0f63f8e96719dc67b382130fd71359e410633b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be47f02784c14a60a08131d0c0f63f8e96719dc67b382130fd71359e410633b8","first_computed_at":"2026-07-05T02:04:25.999605Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:04:25.999605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zwqh4pz9ublWGXH6boWYji8uQf0ct/ISIu7255+gDk0vLQzgaSKTPwys3/xmCuaD6wuiAcZqx6xio/UN6KdkBg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:04:26.000012Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.01022","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be152fc6196897b1e1f4c736b60f9f372b481a3d3f65965ca55d94cd9ace90a2","sha256:19ecebe517122f2c1510a6691b1171a58dd7ab629b98beb4d4282e77ed8366ac"],"state_sha256":"6c6cd8599e8b129bdc5f52d39f6027382837105dd5cd34f134146869304b4abf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tG2WURZY9Gl1x2N7i2WenZDSWlZXzsoU4tktddsFPQz4PWlpevJdKO7xn4+RDHvFJ3lOnWwVt65o2p+s1kuMAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T13:18:38.210480Z","bundle_sha256":"35243cb363b37dfed78c8cc85b9de925733cd8b6ba27d45fb51e60dbd68060da"}}