{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:N53TV7BUMQDCJVYQFI2AAA7RC2","short_pith_number":"pith:N53TV7BU","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"},"canonical_sha256":"6f773afc34640624d7102a340003f11685a5956d98752e6fd05429e23654df59","source":{"kind":"arxiv","id":"1901.08029","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.08029","created_at":"2026-05-17T23:42:53Z"},{"alias_kind":"arxiv_version","alias_value":"1901.08029v2","created_at":"2026-05-17T23:42:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08029","created_at":"2026-05-17T23:42:53Z"},{"alias_kind":"pith_short_12","alias_value":"N53TV7BUMQDC","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"N53TV7BUMQDCJVYQ","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"N53TV7BU","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:N53TV7BUMQDCJVYQFI2AAA7RC2","target":"record","payload":{"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"},"canonical_sha256":"6f773afc34640624d7102a340003f11685a5956d98752e6fd05429e23654df59","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"},"source_kind":"arxiv","source_id":"1901.08029","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":"2026-05-17T23:42:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tuJA3cJY3OED5b/88tMvJcCdzIQO0a9+fqC63CsSRlpsnN5epkbBFwEvGvX1TeGMYQKLNsFdI7WmHWScvQEoCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:04:00.635933Z"},"content_sha256":"05d7f1e58d054c7005afd0e18dc0177f719408cb81059d80dcf72c46b9aa284c","schema_version":"1.0","event_id":"sha256:05d7f1e58d054c7005afd0e18dc0177f719408cb81059d80dcf72c46b9aa284c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:N53TV7BUMQDCJVYQFI2AAA7RC2","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:42:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M0S/3wyLWh8x4/uhjjqQJGimAQBiLg5yQNb7fXitMFvmBuxZs2M/DvtFd0SwuYY3YCpxeSm6QVx3TyMYPEWQCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:04:00.636625Z"},"content_sha256":"689d57eafadc900bb0e242a688ed8b2ae2bc4d220206213b1a6833052afde9af","schema_version":"1.0","event_id":"sha256:689d57eafadc900bb0e242a688ed8b2ae2bc4d220206213b1a6833052afde9af"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N53TV7BUMQDCJVYQFI2AAA7RC2/bundle.json","state_url":"https://pith.science/pith/N53TV7BUMQDCJVYQFI2AAA7RC2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N53TV7BUMQDCJVYQFI2AAA7RC2/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":"2026-05-25T21:04:00Z","links":{"resolver":"https://pith.science/pith/N53TV7BUMQDCJVYQFI2AAA7RC2","bundle":"https://pith.science/pith/N53TV7BUMQDCJVYQFI2AAA7RC2/bundle.json","state":"https://pith.science/pith/N53TV7BUMQDCJVYQFI2AAA7RC2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N53TV7BUMQDCJVYQFI2AAA7RC2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:N53TV7BUMQDCJVYQFI2AAA7RC2","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":"6af330ede036ceaf9012dfac60e113df74a7e7bacd031098840d3b53ecd530ad","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-23T18:03:55Z","title_canon_sha256":"446bde30b470d955e7a777b182f8fb038f930257c69adf9375861dc5fa815189"},"schema_version":"1.0","source":{"id":"1901.08029","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.08029","created_at":"2026-05-17T23:42:53Z"},{"alias_kind":"arxiv_version","alias_value":"1901.08029v2","created_at":"2026-05-17T23:42:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08029","created_at":"2026-05-17T23:42:53Z"},{"alias_kind":"pith_short_12","alias_value":"N53TV7BUMQDC","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"N53TV7BUMQDCJVYQ","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"N53TV7BU","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:689d57eafadc900bb0e242a688ed8b2ae2bc4d220206213b1a6833052afde9af","target":"graph","created_at":"2026-05-17T23:42:53Z","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":"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}","authors_text":"Adish Singla, David C. Parkes, Goran Radanovic, Rati Devidze","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-23T18:03:55Z","title":"Learning to Collaborate in Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08029","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":"sha256:05d7f1e58d054c7005afd0e18dc0177f719408cb81059d80dcf72c46b9aa284c","target":"record","created_at":"2026-05-17T23:42:53Z","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":"6af330ede036ceaf9012dfac60e113df74a7e7bacd031098840d3b53ecd530ad","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-23T18:03:55Z","title_canon_sha256":"446bde30b470d955e7a777b182f8fb038f930257c69adf9375861dc5fa815189"},"schema_version":"1.0","source":{"id":"1901.08029","kind":"arxiv","version":2}},"canonical_sha256":"6f773afc34640624d7102a340003f11685a5956d98752e6fd05429e23654df59","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f773afc34640624d7102a340003f11685a5956d98752e6fd05429e23654df59","first_computed_at":"2026-05-17T23:42:53.444245Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:53.444245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"INM1fmnysMRbk/YCFk0XK4eXJ+rYpsaYx9SlVroiLk/LEwQl8GMS/0dv0LX3O1EYaz7S5ZJkXCKgreYTegSMAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:53.444815Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.08029","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05d7f1e58d054c7005afd0e18dc0177f719408cb81059d80dcf72c46b9aa284c","sha256:689d57eafadc900bb0e242a688ed8b2ae2bc4d220206213b1a6833052afde9af"],"state_sha256":"59ddf9d9981922fb06b08433375f107dc802b1ccc7c29e2078624d3e1c2065bc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z/z+IMSdAmk25owAAVFaZKPgKpfGQcwvWAz4zWXLzDJBNrls7fBJIXtti1vuylQVbNzKRVoKlN4PdqulDJWaBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T21:04:00.640555Z","bundle_sha256":"d596d00aed932622d2e9c177bc87a6d522cce2bc255d3f8d3958f962a252b242"}}