{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:UI6OOVTTDJ5COWBIW6JTGHLWWL","short_pith_number":"pith:UI6OOVTT","canonical_record":{"source":{"id":"2106.12024","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-22T19:20:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ea4f94de0f4623e4721a9879c79ea6fa59bd9c07cf257249e35ab8695c0b334f","abstract_canon_sha256":"557c7c20525750256e779bf6db5d6edb0b113aebf80078f2aaa44008f712e88e"},"schema_version":"1.0"},"canonical_sha256":"a23ce756731a7a275828b793331d76b2fcefad2f76d207cd4737b5becd52c72f","source":{"kind":"arxiv","id":"2106.12024","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.12024","created_at":"2026-07-05T02:51:41Z"},{"alias_kind":"arxiv_version","alias_value":"2106.12024v1","created_at":"2026-07-05T02:51:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.12024","created_at":"2026-07-05T02:51:41Z"},{"alias_kind":"pith_short_12","alias_value":"UI6OOVTTDJ5C","created_at":"2026-07-05T02:51:41Z"},{"alias_kind":"pith_short_16","alias_value":"UI6OOVTTDJ5COWBI","created_at":"2026-07-05T02:51:41Z"},{"alias_kind":"pith_short_8","alias_value":"UI6OOVTT","created_at":"2026-07-05T02:51:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:UI6OOVTTDJ5COWBIW6JTGHLWWL","target":"record","payload":{"canonical_record":{"source":{"id":"2106.12024","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-22T19:20:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ea4f94de0f4623e4721a9879c79ea6fa59bd9c07cf257249e35ab8695c0b334f","abstract_canon_sha256":"557c7c20525750256e779bf6db5d6edb0b113aebf80078f2aaa44008f712e88e"},"schema_version":"1.0"},"canonical_sha256":"a23ce756731a7a275828b793331d76b2fcefad2f76d207cd4737b5becd52c72f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:51:41.708682Z","signature_b64":"IM54jBQyaKFdcSx2mioXRM9yf2AI+setRZnqIXbXK/eYNqO3rUxwoY8bXLYSx4V/4JaSmnCHf2UrQPRi1sW5Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a23ce756731a7a275828b793331d76b2fcefad2f76d207cd4737b5becd52c72f","last_reissued_at":"2026-07-05T02:51:41.708229Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:51:41.708229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.12024","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":"2026-07-05T02:51:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2eyUBdGkEE7Zcooh+3cim3D3+vsB6Pq3F3LKrTL9LegIqcyEqYJaXj14PuPZbWa9ev6rDS51pAUu0/RPlJQMAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T04:24:24.234165Z"},"content_sha256":"173f8a7557158853a26e3d5725bc36c43cb328d5fc683b781b79233978cb1d89","schema_version":"1.0","event_id":"sha256:173f8a7557158853a26e3d5725bc36c43cb328d5fc683b781b79233978cb1d89"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:UI6OOVTTDJ5COWBIW6JTGHLWWL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Q-Learning Lagrange Policies for Multi-Action Restless Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Arpita Biswas, Jackson A. Killian, Milind Tambe, Sanket Shah","submitted_at":"2021-06-22T19:20:09Z","abstract_excerpt":"Multi-action restless multi-armed bandits (RMABs) are a powerful framework for constrained resource allocation in which $N$ independent processes are managed. However, previous work only study the offline setting where problem dynamics are known. We address this restrictive assumption, designing the first algorithms for learning good policies for Multi-action RMABs online using combinations of Lagrangian relaxation and Q-learning. Our first approach, MAIQL, extends a method for Q-learning the Whittle index in binary-action RMABs to the multi-action setting. We derive a generalized update rule "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.12024","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2106.12024/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":"2026-07-05T02:51:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2VrgvStJU2FU4nHUfPZyU4Z8JydEkCA6UpkNZnTVzAVyMYZzqbf5jWGdugH2hv6s9+/+u0zF2/GPGuewpjwyAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T04:24:24.234725Z"},"content_sha256":"a38b28e9ed5f7ce4689073027b02ef7a11279ce71fb47350c845284134e6ce68","schema_version":"1.0","event_id":"sha256:a38b28e9ed5f7ce4689073027b02ef7a11279ce71fb47350c845284134e6ce68"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UI6OOVTTDJ5COWBIW6JTGHLWWL/bundle.json","state_url":"https://pith.science/pith/UI6OOVTTDJ5COWBIW6JTGHLWWL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UI6OOVTTDJ5COWBIW6JTGHLWWL/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":"2026-08-21T04:24:24Z","links":{"resolver":"https://pith.science/pith/UI6OOVTTDJ5COWBIW6JTGHLWWL","bundle":"https://pith.science/pith/UI6OOVTTDJ5COWBIW6JTGHLWWL/bundle.json","state":"https://pith.science/pith/UI6OOVTTDJ5COWBIW6JTGHLWWL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UI6OOVTTDJ5COWBIW6JTGHLWWL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:UI6OOVTTDJ5COWBIW6JTGHLWWL","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":"557c7c20525750256e779bf6db5d6edb0b113aebf80078f2aaa44008f712e88e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-22T19:20:09Z","title_canon_sha256":"ea4f94de0f4623e4721a9879c79ea6fa59bd9c07cf257249e35ab8695c0b334f"},"schema_version":"1.0","source":{"id":"2106.12024","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.12024","created_at":"2026-07-05T02:51:41Z"},{"alias_kind":"arxiv_version","alias_value":"2106.12024v1","created_at":"2026-07-05T02:51:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.12024","created_at":"2026-07-05T02:51:41Z"},{"alias_kind":"pith_short_12","alias_value":"UI6OOVTTDJ5C","created_at":"2026-07-05T02:51:41Z"},{"alias_kind":"pith_short_16","alias_value":"UI6OOVTTDJ5COWBI","created_at":"2026-07-05T02:51:41Z"},{"alias_kind":"pith_short_8","alias_value":"UI6OOVTT","created_at":"2026-07-05T02:51:41Z"}],"graph_snapshots":[{"event_id":"sha256:a38b28e9ed5f7ce4689073027b02ef7a11279ce71fb47350c845284134e6ce68","target":"graph","created_at":"2026-07-05T02:51:41Z","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/2106.12024/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-action restless multi-armed bandits (RMABs) are a powerful framework for constrained resource allocation in which $N$ independent processes are managed. However, previous work only study the offline setting where problem dynamics are known. We address this restrictive assumption, designing the first algorithms for learning good policies for Multi-action RMABs online using combinations of Lagrangian relaxation and Q-learning. Our first approach, MAIQL, extends a method for Q-learning the Whittle index in binary-action RMABs to the multi-action setting. We derive a generalized update rule ","authors_text":"Arpita Biswas, Jackson A. Killian, Milind Tambe, Sanket Shah","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-22T19:20:09Z","title":"Q-Learning Lagrange Policies for Multi-Action Restless Bandits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.12024","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":"sha256:173f8a7557158853a26e3d5725bc36c43cb328d5fc683b781b79233978cb1d89","target":"record","created_at":"2026-07-05T02:51:41Z","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":"557c7c20525750256e779bf6db5d6edb0b113aebf80078f2aaa44008f712e88e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-22T19:20:09Z","title_canon_sha256":"ea4f94de0f4623e4721a9879c79ea6fa59bd9c07cf257249e35ab8695c0b334f"},"schema_version":"1.0","source":{"id":"2106.12024","kind":"arxiv","version":1}},"canonical_sha256":"a23ce756731a7a275828b793331d76b2fcefad2f76d207cd4737b5becd52c72f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a23ce756731a7a275828b793331d76b2fcefad2f76d207cd4737b5becd52c72f","first_computed_at":"2026-07-05T02:51:41.708229Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:51:41.708229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IM54jBQyaKFdcSx2mioXRM9yf2AI+setRZnqIXbXK/eYNqO3rUxwoY8bXLYSx4V/4JaSmnCHf2UrQPRi1sW5Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:51:41.708682Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.12024","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:173f8a7557158853a26e3d5725bc36c43cb328d5fc683b781b79233978cb1d89","sha256:a38b28e9ed5f7ce4689073027b02ef7a11279ce71fb47350c845284134e6ce68"],"state_sha256":"30851d37629f5e06a36d5140cb540d5ecde934a9583815f62ffbe833c6bd4ffb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v444bVt5LzUUj7cbF4yliPqx6vhFUd9EHi1KmvZV+ves3/nr1eKqtgUluMKf5zLIh/ABWUtJLQJNuSdVpDchDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T04:24:24.239211Z","bundle_sha256":"071a0ab69e099cb5378edc727b733e0a75e7c519c3937caa87737abad21cf6da"}}