{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:7S2MFL5BRIADZU6MRE2DJVCXXJ","short_pith_number":"pith:7S2MFL5B","schema_version":"1.0","canonical_sha256":"fcb4c2afa18a003cd3cc893434d457ba5e3c4e8915916d45fbceada80150200e","source":{"kind":"arxiv","id":"2002.12435","version":5},"attestation_state":"computed","paper":{"title":"Learning in Markov Decision Processes under Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Ness B. Shroff, Rahul Singh","submitted_at":"2020-02-27T20:58:39Z","abstract_excerpt":"We consider reinforcement learning (RL) in Markov Decision Processes in which an agent repeatedly interacts with an environment that is modeled by a controlled Markov process. At each time step $t$, it earns a reward, and also incurs a cost-vector consisting of $M$ costs. We design model-based RL algorithms that maximize the cumulative reward earned over a time horizon of $T$ time-steps, while simultaneously ensuring that the average values of the $M$ cost expenditures are bounded by agent-specified thresholds $c^{ub}_i,i=1,2,\\ldots,M$.\n  In order to measure the performance of a reinforcement "},"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":"2002.12435","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-27T20:58:39Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"bb053bb413aaef2dbfaade3229a9206d8e89101699aaa76356b3cd4bb3c620b2","abstract_canon_sha256":"9f4b99016d922aefa2e8e73683f9fbfc088b0ab38fd60f749680d781777aad42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:23.112386Z","signature_b64":"RQsw7ot0hVQPgFi+Yl5pMms9h1gnvbsXj6XTCxvRTYVEvYlqscs6NzR2eEMYNHt8KnrDuOc75Ch9cLXZM0WXDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcb4c2afa18a003cd3cc893434d457ba5e3c4e8915916d45fbceada80150200e","last_reissued_at":"2026-07-05T05:51:23.111884Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:23.111884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning in Markov Decision Processes under Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Ness B. Shroff, Rahul Singh","submitted_at":"2020-02-27T20:58:39Z","abstract_excerpt":"We consider reinforcement learning (RL) in Markov Decision Processes in which an agent repeatedly interacts with an environment that is modeled by a controlled Markov process. At each time step $t$, it earns a reward, and also incurs a cost-vector consisting of $M$ costs. We design model-based RL algorithms that maximize the cumulative reward earned over a time horizon of $T$ time-steps, while simultaneously ensuring that the average values of the $M$ cost expenditures are bounded by agent-specified thresholds $c^{ub}_i,i=1,2,\\ldots,M$.\n  In order to measure the performance of a reinforcement "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.12435","kind":"arxiv","version":5},"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/2002.12435/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2002.12435","created_at":"2026-07-05T05:51:23.111940+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.12435v5","created_at":"2026-07-05T05:51:23.111940+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.12435","created_at":"2026-07-05T05:51:23.111940+00:00"},{"alias_kind":"pith_short_12","alias_value":"7S2MFL5BRIAD","created_at":"2026-07-05T05:51:23.111940+00:00"},{"alias_kind":"pith_short_16","alias_value":"7S2MFL5BRIADZU6M","created_at":"2026-07-05T05:51:23.111940+00:00"},{"alias_kind":"pith_short_8","alias_value":"7S2MFL5B","created_at":"2026-07-05T05:51:23.111940+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.21841","citing_title":"An Optimistic Algorithm for online CMDPS with Anytime Adversarial Constraints","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7S2MFL5BRIADZU6MRE2DJVCXXJ","json":"https://pith.science/pith/7S2MFL5BRIADZU6MRE2DJVCXXJ.json","graph_json":"https://pith.science/api/pith-number/7S2MFL5BRIADZU6MRE2DJVCXXJ/graph.json","events_json":"https://pith.science/api/pith-number/7S2MFL5BRIADZU6MRE2DJVCXXJ/events.json","paper":"https://pith.science/paper/7S2MFL5B"},"agent_actions":{"view_html":"https://pith.science/pith/7S2MFL5BRIADZU6MRE2DJVCXXJ","download_json":"https://pith.science/pith/7S2MFL5BRIADZU6MRE2DJVCXXJ.json","view_paper":"https://pith.science/paper/7S2MFL5B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.12435&json=true","fetch_graph":"https://pith.science/api/pith-number/7S2MFL5BRIADZU6MRE2DJVCXXJ/graph.json","fetch_events":"https://pith.science/api/pith-number/7S2MFL5BRIADZU6MRE2DJVCXXJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7S2MFL5BRIADZU6MRE2DJVCXXJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7S2MFL5BRIADZU6MRE2DJVCXXJ/action/storage_attestation","attest_author":"https://pith.science/pith/7S2MFL5BRIADZU6MRE2DJVCXXJ/action/author_attestation","sign_citation":"https://pith.science/pith/7S2MFL5BRIADZU6MRE2DJVCXXJ/action/citation_signature","submit_replication":"https://pith.science/pith/7S2MFL5BRIADZU6MRE2DJVCXXJ/action/replication_record"}},"created_at":"2026-07-05T05:51:23.111940+00:00","updated_at":"2026-07-05T05:51:23.111940+00:00"}