{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:FDLQ2U6PWJCO6D54DWULJNDTTZ","short_pith_number":"pith:FDLQ2U6P","canonical_record":{"source":{"id":"2102.04939","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-09T16:49:58Z","cross_cats_sorted":[],"title_canon_sha256":"d171dc5535f7a1d443d5904c95dd8d6d7d74d89f83abba41f0c10385bca5c328","abstract_canon_sha256":"654be6527e1c462576727c8c752a97e44f73801dc06a6ebd7047bff41e9fb422"},"schema_version":"1.0"},"canonical_sha256":"28d70d53cfb244ef0fbc1da8b4b4739e7a0ff5d318f50b25384009e733868aa3","source":{"kind":"arxiv","id":"2102.04939","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.04939","created_at":"2026-07-05T02:14:06Z"},{"alias_kind":"arxiv_version","alias_value":"2102.04939v1","created_at":"2026-07-05T02:14:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.04939","created_at":"2026-07-05T02:14:06Z"},{"alias_kind":"pith_short_12","alias_value":"FDLQ2U6PWJCO","created_at":"2026-07-05T02:14:06Z"},{"alias_kind":"pith_short_16","alias_value":"FDLQ2U6PWJCO6D54","created_at":"2026-07-05T02:14:06Z"},{"alias_kind":"pith_short_8","alias_value":"FDLQ2U6P","created_at":"2026-07-05T02:14:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:FDLQ2U6PWJCO6D54DWULJNDTTZ","target":"record","payload":{"canonical_record":{"source":{"id":"2102.04939","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-09T16:49:58Z","cross_cats_sorted":[],"title_canon_sha256":"d171dc5535f7a1d443d5904c95dd8d6d7d74d89f83abba41f0c10385bca5c328","abstract_canon_sha256":"654be6527e1c462576727c8c752a97e44f73801dc06a6ebd7047bff41e9fb422"},"schema_version":"1.0"},"canonical_sha256":"28d70d53cfb244ef0fbc1da8b4b4739e7a0ff5d318f50b25384009e733868aa3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:14:06.505801Z","signature_b64":"WLwf1P6LKvOVKC4JhIbZtfySlJvSUqHTq/nb7AApt42i892r7K1gRLrtqBzndbqTx+/y9YOqOix5Zc5VLiGuBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28d70d53cfb244ef0fbc1da8b4b4739e7a0ff5d318f50b25384009e733868aa3","last_reissued_at":"2026-07-05T02:14:06.505361Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:14:06.505361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.04939","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":"2026-07-05T02:14:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l+8SeJkolaTEPjb6O5t66OZO4dzRC/EzuvSAOU7YW4iwFa5FO/II8lQ3/2zkB8bQq4DvFjFvAERJkjiM7FPZCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:11:50.903086Z"},"content_sha256":"69c95f3b5c44d6fa113fecf9666c9ff176f0fa0759d970937ff7fe2a6290cbce","schema_version":"1.0","event_id":"sha256:69c95f3b5c44d6fa113fecf9666c9ff176f0fa0759d970937ff7fe2a6290cbce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:FDLQ2U6PWJCO6D54DWULJNDTTZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RL for Latent MDPs: Regret Guarantees and a Lower Bound","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Constantine Caramanis, Jeongyeol Kwon, Shie Mannor, Yonathan Efroni","submitted_at":"2021-02-09T16:49:58Z","abstract_excerpt":"In this work, we consider the regret minimization problem for reinforcement learning in latent Markov Decision Processes (LMDP). In an LMDP, an MDP is randomly drawn from a set of $M$ possible MDPs at the beginning of the interaction, but the identity of the chosen MDP is not revealed to the agent. We first show that a general instance of LMDPs requires at least $\\Omega((SA)^M)$ episodes to even approximate the optimal policy. Then, we consider sufficient assumptions under which learning good policies requires polynomial number of episodes. We show that the key link is a notion of separation b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.04939","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/2102.04939/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":"2026-07-05T02:14:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3gJiQPaz4npkM+RjlBCtE7ni21/mX5nPwEBYyXmUdg4SEPrRPnFI24TQ6d0fPaS8H7FqcEd9ux7ep5xYgtoWBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:11:50.903774Z"},"content_sha256":"159fe2e0fc327ff59bd4fcb3201199fce2f50e962664145a3728f1801d0e8525","schema_version":"1.0","event_id":"sha256:159fe2e0fc327ff59bd4fcb3201199fce2f50e962664145a3728f1801d0e8525"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FDLQ2U6PWJCO6D54DWULJNDTTZ/bundle.json","state_url":"https://pith.science/pith/FDLQ2U6PWJCO6D54DWULJNDTTZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FDLQ2U6PWJCO6D54DWULJNDTTZ/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":"2026-08-10T10:11:50Z","links":{"resolver":"https://pith.science/pith/FDLQ2U6PWJCO6D54DWULJNDTTZ","bundle":"https://pith.science/pith/FDLQ2U6PWJCO6D54DWULJNDTTZ/bundle.json","state":"https://pith.science/pith/FDLQ2U6PWJCO6D54DWULJNDTTZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FDLQ2U6PWJCO6D54DWULJNDTTZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FDLQ2U6PWJCO6D54DWULJNDTTZ","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":"654be6527e1c462576727c8c752a97e44f73801dc06a6ebd7047bff41e9fb422","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-09T16:49:58Z","title_canon_sha256":"d171dc5535f7a1d443d5904c95dd8d6d7d74d89f83abba41f0c10385bca5c328"},"schema_version":"1.0","source":{"id":"2102.04939","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.04939","created_at":"2026-07-05T02:14:06Z"},{"alias_kind":"arxiv_version","alias_value":"2102.04939v1","created_at":"2026-07-05T02:14:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.04939","created_at":"2026-07-05T02:14:06Z"},{"alias_kind":"pith_short_12","alias_value":"FDLQ2U6PWJCO","created_at":"2026-07-05T02:14:06Z"},{"alias_kind":"pith_short_16","alias_value":"FDLQ2U6PWJCO6D54","created_at":"2026-07-05T02:14:06Z"},{"alias_kind":"pith_short_8","alias_value":"FDLQ2U6P","created_at":"2026-07-05T02:14:06Z"}],"graph_snapshots":[{"event_id":"sha256:159fe2e0fc327ff59bd4fcb3201199fce2f50e962664145a3728f1801d0e8525","target":"graph","created_at":"2026-07-05T02:14:06Z","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/2102.04939/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we consider the regret minimization problem for reinforcement learning in latent Markov Decision Processes (LMDP). In an LMDP, an MDP is randomly drawn from a set of $M$ possible MDPs at the beginning of the interaction, but the identity of the chosen MDP is not revealed to the agent. We first show that a general instance of LMDPs requires at least $\\Omega((SA)^M)$ episodes to even approximate the optimal policy. Then, we consider sufficient assumptions under which learning good policies requires polynomial number of episodes. We show that the key link is a notion of separation b","authors_text":"Constantine Caramanis, Jeongyeol Kwon, Shie Mannor, Yonathan Efroni","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-09T16:49:58Z","title":"RL for Latent MDPs: Regret Guarantees and a Lower Bound"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.04939","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":"sha256:69c95f3b5c44d6fa113fecf9666c9ff176f0fa0759d970937ff7fe2a6290cbce","target":"record","created_at":"2026-07-05T02:14:06Z","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":"654be6527e1c462576727c8c752a97e44f73801dc06a6ebd7047bff41e9fb422","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-09T16:49:58Z","title_canon_sha256":"d171dc5535f7a1d443d5904c95dd8d6d7d74d89f83abba41f0c10385bca5c328"},"schema_version":"1.0","source":{"id":"2102.04939","kind":"arxiv","version":1}},"canonical_sha256":"28d70d53cfb244ef0fbc1da8b4b4739e7a0ff5d318f50b25384009e733868aa3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28d70d53cfb244ef0fbc1da8b4b4739e7a0ff5d318f50b25384009e733868aa3","first_computed_at":"2026-07-05T02:14:06.505361Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:14:06.505361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WLwf1P6LKvOVKC4JhIbZtfySlJvSUqHTq/nb7AApt42i892r7K1gRLrtqBzndbqTx+/y9YOqOix5Zc5VLiGuBA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:14:06.505801Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.04939","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:69c95f3b5c44d6fa113fecf9666c9ff176f0fa0759d970937ff7fe2a6290cbce","sha256:159fe2e0fc327ff59bd4fcb3201199fce2f50e962664145a3728f1801d0e8525"],"state_sha256":"dc3381998693435224cfbe05382dcd5af3ec81ccc11d00dba056ea9973858a62"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HsQmp1tQ2Nh0wVJqdVfZAegDGRXHMdwWEBYpodz4vnCqnqXpnKqfF7NcGz052zD0XysfA39Hi4Xgheiz90iZCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T10:11:50.908667Z","bundle_sha256":"25f9f872bdb234d8cd461df49718f87012b85af33349ff92e0e20aa5998fec60"}}