{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:N53TV7BUMQDCJVYQFI2AAA7RC2","short_pith_number":"pith:N53TV7BU","schema_version":"1.0","canonical_sha256":"6f773afc34640624d7102a340003f11685a5956d98752e6fd05429e23654df59","source":{"kind":"arxiv","id":"1901.08029","version":2},"attestation_state":"computed","paper":{"title":"Learning to Collaborate in Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adish Singla, David C. Parkes, Goran Radanovic, Rati Devidze","submitted_at":"2019-01-23T18:03:55Z","abstract_excerpt":"We consider a two-agent MDP framework where agents repeatedly solve a task in a collaborative setting. We study the problem of designing a learning algorithm for the first agent (A1) that facilitates a successful collaboration even in cases when the second agent (A2) is adapting its policy in an unknown way. The key challenge in our setting is that the first agent faces non-stationarity in rewards and transitions because of the adaptive behavior of the second agent.\n  We design novel online learning algorithms for agent A1 whose regret decays as $O(T^{\\max\\{1-\\frac{3}{7} \\cdot \\alpha, \\frac{1}"},"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":"1901.08029","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-23T18:03:55Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"446bde30b470d955e7a777b182f8fb038f930257c69adf9375861dc5fa815189","abstract_canon_sha256":"6af330ede036ceaf9012dfac60e113df74a7e7bacd031098840d3b53ecd530ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:53.444815Z","signature_b64":"INM1fmnysMRbk/YCFk0XK4eXJ+rYpsaYx9SlVroiLk/LEwQl8GMS/0dv0LX3O1EYaz7S5ZJkXCKgreYTegSMAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f773afc34640624d7102a340003f11685a5956d98752e6fd05429e23654df59","last_reissued_at":"2026-05-17T23:42:53.444245Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:53.444245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Collaborate in Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adish Singla, David C. Parkes, Goran Radanovic, Rati Devidze","submitted_at":"2019-01-23T18:03:55Z","abstract_excerpt":"We consider a two-agent MDP framework where agents repeatedly solve a task in a collaborative setting. We study the problem of designing a learning algorithm for the first agent (A1) that facilitates a successful collaboration even in cases when the second agent (A2) is adapting its policy in an unknown way. The key challenge in our setting is that the first agent faces non-stationarity in rewards and transitions because of the adaptive behavior of the second agent.\n  We design novel online learning algorithms for agent A1 whose regret decays as $O(T^{\\max\\{1-\\frac{3}{7} \\cdot \\alpha, \\frac{1}"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08029","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1901.08029","created_at":"2026-05-17T23:42:53.444327+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.08029v2","created_at":"2026-05-17T23:42:53.444327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08029","created_at":"2026-05-17T23:42:53.444327+00:00"},{"alias_kind":"pith_short_12","alias_value":"N53TV7BUMQDC","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"N53TV7BUMQDCJVYQ","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"N53TV7BU","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/N53TV7BUMQDCJVYQFI2AAA7RC2","json":"https://pith.science/pith/N53TV7BUMQDCJVYQFI2AAA7RC2.json","graph_json":"https://pith.science/api/pith-number/N53TV7BUMQDCJVYQFI2AAA7RC2/graph.json","events_json":"https://pith.science/api/pith-number/N53TV7BUMQDCJVYQFI2AAA7RC2/events.json","paper":"https://pith.science/paper/N53TV7BU"},"agent_actions":{"view_html":"https://pith.science/pith/N53TV7BUMQDCJVYQFI2AAA7RC2","download_json":"https://pith.science/pith/N53TV7BUMQDCJVYQFI2AAA7RC2.json","view_paper":"https://pith.science/paper/N53TV7BU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.08029&json=true","fetch_graph":"https://pith.science/api/pith-number/N53TV7BUMQDCJVYQFI2AAA7RC2/graph.json","fetch_events":"https://pith.science/api/pith-number/N53TV7BUMQDCJVYQFI2AAA7RC2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N53TV7BUMQDCJVYQFI2AAA7RC2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N53TV7BUMQDCJVYQFI2AAA7RC2/action/storage_attestation","attest_author":"https://pith.science/pith/N53TV7BUMQDCJVYQFI2AAA7RC2/action/author_attestation","sign_citation":"https://pith.science/pith/N53TV7BUMQDCJVYQFI2AAA7RC2/action/citation_signature","submit_replication":"https://pith.science/pith/N53TV7BUMQDCJVYQFI2AAA7RC2/action/replication_record"}},"created_at":"2026-05-17T23:42:53.444327+00:00","updated_at":"2026-05-17T23:42:53.444327+00:00"}