{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:PBYDDC7XDCR5E2VLCBTX4EJYPH","short_pith_number":"pith:PBYDDC7X","schema_version":"1.0","canonical_sha256":"7870318bf718a3d26aab10677e113879eeef14bcb123f246073f27ccb52250d8","source":{"kind":"arxiv","id":"1901.01325","version":1},"attestation_state":"computed","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1901.01325","created_at":"2026-05-17T23:56:52.254057+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.01325v1","created_at":"2026-05-17T23:56:52.254057+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.01325","created_at":"2026-05-17T23:56:52.254057+00:00"},{"alias_kind":"pith_short_12","alias_value":"PBYDDC7XDCR5","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"PBYDDC7XDCR5E2VL","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"PBYDDC7X","created_at":"2026-05-18T12:33:24.271573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PBYDDC7XDCR5E2VLCBTX4EJYPH","json":"https://pith.science/pith/PBYDDC7XDCR5E2VLCBTX4EJYPH.json","graph_json":"https://pith.science/api/pith-number/PBYDDC7XDCR5E2VLCBTX4EJYPH/graph.json","events_json":"https://pith.science/api/pith-number/PBYDDC7XDCR5E2VLCBTX4EJYPH/events.json","paper":"https://pith.science/paper/PBYDDC7X"},"agent_actions":{"view_html":"https://pith.science/pith/PBYDDC7XDCR5E2VLCBTX4EJYPH","download_json":"https://pith.science/pith/PBYDDC7XDCR5E2VLCBTX4EJYPH.json","view_paper":"https://pith.science/paper/PBYDDC7X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.01325&json=true","fetch_graph":"https://pith.science/api/pith-number/PBYDDC7XDCR5E2VLCBTX4EJYPH/graph.json","fetch_events":"https://pith.science/api/pith-number/PBYDDC7XDCR5E2VLCBTX4EJYPH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PBYDDC7XDCR5E2VLCBTX4EJYPH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PBYDDC7XDCR5E2VLCBTX4EJYPH/action/storage_attestation","attest_author":"https://pith.science/pith/PBYDDC7XDCR5E2VLCBTX4EJYPH/action/author_attestation","sign_citation":"https://pith.science/pith/PBYDDC7XDCR5E2VLCBTX4EJYPH/action/citation_signature","submit_replication":"https://pith.science/pith/PBYDDC7XDCR5E2VLCBTX4EJYPH/action/replication_record"}},"created_at":"2026-05-17T23:56:52.254057+00:00","updated_at":"2026-05-17T23:56:52.254057+00:00"}