{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:UXXJB2FTTLGQ6GYK56GIK54YHZ","short_pith_number":"pith:UXXJB2FT","canonical_record":{"source":{"id":"2010.08891","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-18T00:11:45Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"8778938b07ee1611f8722d99860104a39df539129edb6e0958171f81bdac4b01","abstract_canon_sha256":"9462a2414a48185dd45c4985ed798636ee0da45ba66f02e83e10f9d9ffdafcab"},"schema_version":"1.0"},"canonical_sha256":"a5ee90e8b39acd0f1b0aef8c8577983e649742236cb29ce0add94a9d9f8eee93","source":{"kind":"arxiv","id":"2010.08891","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.08891","created_at":"2026-07-05T10:09:38Z"},{"alias_kind":"arxiv_version","alias_value":"2010.08891v2","created_at":"2026-07-05T10:09:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.08891","created_at":"2026-07-05T10:09:38Z"},{"alias_kind":"pith_short_12","alias_value":"UXXJB2FTTLGQ","created_at":"2026-07-05T10:09:38Z"},{"alias_kind":"pith_short_16","alias_value":"UXXJB2FTTLGQ6GYK","created_at":"2026-07-05T10:09:38Z"},{"alias_kind":"pith_short_8","alias_value":"UXXJB2FT","created_at":"2026-07-05T10:09:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:UXXJB2FTTLGQ6GYK56GIK54YHZ","target":"record","payload":{"canonical_record":{"source":{"id":"2010.08891","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-18T00:11:45Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"8778938b07ee1611f8722d99860104a39df539129edb6e0958171f81bdac4b01","abstract_canon_sha256":"9462a2414a48185dd45c4985ed798636ee0da45ba66f02e83e10f9d9ffdafcab"},"schema_version":"1.0"},"canonical_sha256":"a5ee90e8b39acd0f1b0aef8c8577983e649742236cb29ce0add94a9d9f8eee93","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:38.046352Z","signature_b64":"VuHhg2ZWDwqq+TTMjK5DJzrlmfDxC5kTqVvpJHdCcv1VzobicXJYjcTOcaH+rVHsmTN+z8HPTReXOWgSyXb0CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5ee90e8b39acd0f1b0aef8c8577983e649742236cb29ce0add94a9d9f8eee93","last_reissued_at":"2026-07-05T10:09:38.045951Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:38.045951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.08891","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":"2026-07-05T10:09:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cnXr0FnI6y8xw59dowBhlYp99jHQTIt53jElYdOdr00zgzHdR6r3Ig5NW13fdzvvLyvfP24MkP1zIVpSmjoSAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T16:11:23.850555Z"},"content_sha256":"b5e5fd9db00e193f5ed0a830d081f48d630b9470359b98044cbdd95a851437b4","schema_version":"1.0","event_id":"sha256:b5e5fd9db00e193f5ed0a830d081f48d630b9470359b98044cbdd95a851437b4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:UXXJB2FTTLGQ6GYK56GIK54YHZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DeepAveragers: Offline Reinforcement Learning by Solving Derived Non-Parametric MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aayam Shrestha, Alan Fern, Prasad Tadepalli, Stefan Lee","submitted_at":"2020-10-18T00:11:45Z","abstract_excerpt":"We study an approach to offline reinforcement learning (RL) based on optimally solving finitely-represented MDPs derived from a static dataset of experience. This approach can be applied on top of any learned representation and has the potential to easily support multiple solution objectives as well as zero-shot adjustment to changing environments and goals. Our main contribution is to introduce the Deep Averagers with Costs MDP (DAC-MDP) and to investigate its solutions for offline RL. DAC-MDPs are a non-parametric model that can leverage deep representations and account for limited data by i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.08891","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2010.08891/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":"2026-07-05T10:09:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uixwCp2PNGq4wfiRQUj0yMhlQuD9ieiVetpnspw7x1x9yV7vQtfI/1MxrOK7M5UKsDEZqWmGOwmCHbLGc4cMDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T16:11:23.852049Z"},"content_sha256":"d3242c4704948df8eeb1980956df58b40cdbd6d77593f9b63598be8bca7c20aa","schema_version":"1.0","event_id":"sha256:d3242c4704948df8eeb1980956df58b40cdbd6d77593f9b63598be8bca7c20aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UXXJB2FTTLGQ6GYK56GIK54YHZ/bundle.json","state_url":"https://pith.science/pith/UXXJB2FTTLGQ6GYK56GIK54YHZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UXXJB2FTTLGQ6GYK56GIK54YHZ/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":"2026-08-09T16:11:23Z","links":{"resolver":"https://pith.science/pith/UXXJB2FTTLGQ6GYK56GIK54YHZ","bundle":"https://pith.science/pith/UXXJB2FTTLGQ6GYK56GIK54YHZ/bundle.json","state":"https://pith.science/pith/UXXJB2FTTLGQ6GYK56GIK54YHZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UXXJB2FTTLGQ6GYK56GIK54YHZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:UXXJB2FTTLGQ6GYK56GIK54YHZ","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":"9462a2414a48185dd45c4985ed798636ee0da45ba66f02e83e10f9d9ffdafcab","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-18T00:11:45Z","title_canon_sha256":"8778938b07ee1611f8722d99860104a39df539129edb6e0958171f81bdac4b01"},"schema_version":"1.0","source":{"id":"2010.08891","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.08891","created_at":"2026-07-05T10:09:38Z"},{"alias_kind":"arxiv_version","alias_value":"2010.08891v2","created_at":"2026-07-05T10:09:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.08891","created_at":"2026-07-05T10:09:38Z"},{"alias_kind":"pith_short_12","alias_value":"UXXJB2FTTLGQ","created_at":"2026-07-05T10:09:38Z"},{"alias_kind":"pith_short_16","alias_value":"UXXJB2FTTLGQ6GYK","created_at":"2026-07-05T10:09:38Z"},{"alias_kind":"pith_short_8","alias_value":"UXXJB2FT","created_at":"2026-07-05T10:09:38Z"}],"graph_snapshots":[{"event_id":"sha256:d3242c4704948df8eeb1980956df58b40cdbd6d77593f9b63598be8bca7c20aa","target":"graph","created_at":"2026-07-05T10:09:38Z","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/2010.08891/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study an approach to offline reinforcement learning (RL) based on optimally solving finitely-represented MDPs derived from a static dataset of experience. This approach can be applied on top of any learned representation and has the potential to easily support multiple solution objectives as well as zero-shot adjustment to changing environments and goals. Our main contribution is to introduce the Deep Averagers with Costs MDP (DAC-MDP) and to investigate its solutions for offline RL. DAC-MDPs are a non-parametric model that can leverage deep representations and account for limited data by i","authors_text":"Aayam Shrestha, Alan Fern, Prasad Tadepalli, Stefan Lee","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-18T00:11:45Z","title":"DeepAveragers: Offline Reinforcement Learning by Solving Derived Non-Parametric MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.08891","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:b5e5fd9db00e193f5ed0a830d081f48d630b9470359b98044cbdd95a851437b4","target":"record","created_at":"2026-07-05T10:09:38Z","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":"9462a2414a48185dd45c4985ed798636ee0da45ba66f02e83e10f9d9ffdafcab","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-18T00:11:45Z","title_canon_sha256":"8778938b07ee1611f8722d99860104a39df539129edb6e0958171f81bdac4b01"},"schema_version":"1.0","source":{"id":"2010.08891","kind":"arxiv","version":2}},"canonical_sha256":"a5ee90e8b39acd0f1b0aef8c8577983e649742236cb29ce0add94a9d9f8eee93","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a5ee90e8b39acd0f1b0aef8c8577983e649742236cb29ce0add94a9d9f8eee93","first_computed_at":"2026-07-05T10:09:38.045951Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:38.045951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VuHhg2ZWDwqq+TTMjK5DJzrlmfDxC5kTqVvpJHdCcv1VzobicXJYjcTOcaH+rVHsmTN+z8HPTReXOWgSyXb0CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:38.046352Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.08891","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5e5fd9db00e193f5ed0a830d081f48d630b9470359b98044cbdd95a851437b4","sha256:d3242c4704948df8eeb1980956df58b40cdbd6d77593f9b63598be8bca7c20aa"],"state_sha256":"6497bbaa68d72c0d19a5871101b7f6d3a222422a73093f402fa24521f69abaa3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"24nXGz2fqJgce0QVJDlimRM4gMKocm2KP3hxSe9mdoR9ZDB1pvmE7E3AVUPE/hU68R/NhjnS6KUcT3Qr93NmBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T16:11:23.861310Z","bundle_sha256":"293a0b9a2c34f1573ec08514839db9492448dc739306ad1735d7ee8eced1a885"}}