{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:PBYDDC7XDCR5E2VLCBTX4EJYPH","short_pith_number":"pith:PBYDDC7X","canonical_record":{"source":{"id":"1901.01325","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-04T21:59:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a1e862e236730b3e91536421bbabe43f197ab412315736f9e772ee523d858b75","abstract_canon_sha256":"8fa703e823b00a905bb32f5b7d98d64ebd928f4e9e5321cf461cba81f0d4b3b7"},"schema_version":"1.0"},"canonical_sha256":"7870318bf718a3d26aab10677e113879eeef14bcb123f246073f27ccb52250d8","source":{"kind":"arxiv","id":"1901.01325","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.01325","created_at":"2026-05-17T23:56:52Z"},{"alias_kind":"arxiv_version","alias_value":"1901.01325v1","created_at":"2026-05-17T23:56:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.01325","created_at":"2026-05-17T23:56:52Z"},{"alias_kind":"pith_short_12","alias_value":"PBYDDC7XDCR5","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"PBYDDC7XDCR5E2VL","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"PBYDDC7X","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:PBYDDC7XDCR5E2VLCBTX4EJYPH","target":"record","payload":{"canonical_record":{"source":{"id":"1901.01325","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-04T21:59:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a1e862e236730b3e91536421bbabe43f197ab412315736f9e772ee523d858b75","abstract_canon_sha256":"8fa703e823b00a905bb32f5b7d98d64ebd928f4e9e5321cf461cba81f0d4b3b7"},"schema_version":"1.0"},"canonical_sha256":"7870318bf718a3d26aab10677e113879eeef14bcb123f246073f27ccb52250d8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:52.254423Z","signature_b64":"M3jgg8eWIiLedYNl+CqoGDSOYrsuiGt+ZmCG288IFKS4kkjYE/CjA5WcETfutwudrVNUHAYLJrpdMl2zDeX2DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7870318bf718a3d26aab10677e113879eeef14bcb123f246073f27ccb52250d8","last_reissued_at":"2026-05-17T23:56:52.253992Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:52.253992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.01325","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":"2026-05-17T23:56:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hMKDI0GkwzTQd6BRK1HnKahtG1W/kBfDkwkalVgqfgRW+WDsmAS2OedbXMzd1Ss00EI0XaPyMJMM8OFeDIsMCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T13:33:51.733530Z"},"content_sha256":"1d8c8da93d25b662596c5f29735dc87177e7db4d1eeb3010fb297d0981e4ac72","schema_version":"1.0","event_id":"sha256:1d8c8da93d25b662596c5f29735dc87177e7db4d1eeb3010fb297d0981e4ac72"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:PBYDDC7XDCR5E2VLCBTX4EJYPH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimal Decision-Making in Mixed-Agent Partially Observable Stochastic Environments via Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Roi Ceren","submitted_at":"2019-01-04T21:59:28Z","abstract_excerpt":"Optimal decision making with limited or no information in stochastic environments where multiple agents interact is a challenging topic in the realm of artificial intelligence. Reinforcement learning (RL) is a popular approach for arriving at optimal strategies by predicating stimuli, such as the reward for following a strategy, on experience. RL is heavily explored in the single-agent context, but is a nascent concept in multiagent problems. To this end, I propose several principled model-free and partially model-based reinforcement learning approaches for several multiagent settings. In the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.01325","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":"2026-05-17T23:56:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n8oDfWAOUM16e3+ED0FQSUSI0NJqOHJCgH2k9+hfnEiWxQ9vHodQZ5PBFjERKaOSEK5PsJdPoZl5GqgyRPWiAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T13:33:51.733878Z"},"content_sha256":"ead67c8be0b74e53f23e2a513e3d803bf98b964478e6714180300b2d12d65aad","schema_version":"1.0","event_id":"sha256:ead67c8be0b74e53f23e2a513e3d803bf98b964478e6714180300b2d12d65aad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PBYDDC7XDCR5E2VLCBTX4EJYPH/bundle.json","state_url":"https://pith.science/pith/PBYDDC7XDCR5E2VLCBTX4EJYPH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PBYDDC7XDCR5E2VLCBTX4EJYPH/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":"2026-06-08T13:33:51Z","links":{"resolver":"https://pith.science/pith/PBYDDC7XDCR5E2VLCBTX4EJYPH","bundle":"https://pith.science/pith/PBYDDC7XDCR5E2VLCBTX4EJYPH/bundle.json","state":"https://pith.science/pith/PBYDDC7XDCR5E2VLCBTX4EJYPH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PBYDDC7XDCR5E2VLCBTX4EJYPH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:PBYDDC7XDCR5E2VLCBTX4EJYPH","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":"8fa703e823b00a905bb32f5b7d98d64ebd928f4e9e5321cf461cba81f0d4b3b7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-04T21:59:28Z","title_canon_sha256":"a1e862e236730b3e91536421bbabe43f197ab412315736f9e772ee523d858b75"},"schema_version":"1.0","source":{"id":"1901.01325","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.01325","created_at":"2026-05-17T23:56:52Z"},{"alias_kind":"arxiv_version","alias_value":"1901.01325v1","created_at":"2026-05-17T23:56:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.01325","created_at":"2026-05-17T23:56:52Z"},{"alias_kind":"pith_short_12","alias_value":"PBYDDC7XDCR5","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"PBYDDC7XDCR5E2VL","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"PBYDDC7X","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:ead67c8be0b74e53f23e2a513e3d803bf98b964478e6714180300b2d12d65aad","target":"graph","created_at":"2026-05-17T23:56:52Z","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":"Optimal decision making with limited or no information in stochastic environments where multiple agents interact is a challenging topic in the realm of artificial intelligence. Reinforcement learning (RL) is a popular approach for arriving at optimal strategies by predicating stimuli, such as the reward for following a strategy, on experience. RL is heavily explored in the single-agent context, but is a nascent concept in multiagent problems. To this end, I propose several principled model-free and partially model-based reinforcement learning approaches for several multiagent settings. In the ","authors_text":"Roi Ceren","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-04T21:59:28Z","title":"Optimal Decision-Making in Mixed-Agent Partially Observable Stochastic Environments via Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.01325","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":"sha256:1d8c8da93d25b662596c5f29735dc87177e7db4d1eeb3010fb297d0981e4ac72","target":"record","created_at":"2026-05-17T23:56:52Z","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":"8fa703e823b00a905bb32f5b7d98d64ebd928f4e9e5321cf461cba81f0d4b3b7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-04T21:59:28Z","title_canon_sha256":"a1e862e236730b3e91536421bbabe43f197ab412315736f9e772ee523d858b75"},"schema_version":"1.0","source":{"id":"1901.01325","kind":"arxiv","version":1}},"canonical_sha256":"7870318bf718a3d26aab10677e113879eeef14bcb123f246073f27ccb52250d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7870318bf718a3d26aab10677e113879eeef14bcb123f246073f27ccb52250d8","first_computed_at":"2026-05-17T23:56:52.253992Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:56:52.253992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M3jgg8eWIiLedYNl+CqoGDSOYrsuiGt+ZmCG288IFKS4kkjYE/CjA5WcETfutwudrVNUHAYLJrpdMl2zDeX2DQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:56:52.254423Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.01325","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d8c8da93d25b662596c5f29735dc87177e7db4d1eeb3010fb297d0981e4ac72","sha256:ead67c8be0b74e53f23e2a513e3d803bf98b964478e6714180300b2d12d65aad"],"state_sha256":"1435e2d9ecdf67f1127cd9fb651d6cd554e856db2aa1ae58ad347d6b8e34c979"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bITFo0MN2wDxPG+YMcqNokN5fFzxyOVALdstvWh0MmAzgwQPsCz+2iDv7x51wwHYoVB3ENz6Yc+AVpVQmp+ODQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T13:33:51.735717Z","bundle_sha256":"fa632ae751f8cf4b315cadc51024e7ded81424cb8e0a4731ac47d26eacded2f6"}}