{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:URTHULKXL2FGLDQTHWJMBNGAZI","short_pith_number":"pith:URTHULKX","canonical_record":{"source":{"id":"2001.05411","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-15T16:29:30Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"0c699763278e595d5ecf6dc374c2d4cf94638a669971311095bda7028131a298","abstract_canon_sha256":"8072bd88e3350479b29646b37b67316026c52a05a3a769c902f6f9c06a0ca4e3"},"schema_version":"1.0"},"canonical_sha256":"a4667a2d575e8a658e133d92c0b4c0ca34d1370b6122b59d903850e3b38820b3","source":{"kind":"arxiv","id":"2001.05411","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.05411","created_at":"2026-07-05T02:25:09Z"},{"alias_kind":"arxiv_version","alias_value":"2001.05411v3","created_at":"2026-07-05T02:25:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.05411","created_at":"2026-07-05T02:25:09Z"},{"alias_kind":"pith_short_12","alias_value":"URTHULKXL2FG","created_at":"2026-07-05T02:25:09Z"},{"alias_kind":"pith_short_16","alias_value":"URTHULKXL2FGLDQT","created_at":"2026-07-05T02:25:09Z"},{"alias_kind":"pith_short_8","alias_value":"URTHULKX","created_at":"2026-07-05T02:25:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:URTHULKXL2FGLDQTHWJMBNGAZI","target":"record","payload":{"canonical_record":{"source":{"id":"2001.05411","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-15T16:29:30Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"0c699763278e595d5ecf6dc374c2d4cf94638a669971311095bda7028131a298","abstract_canon_sha256":"8072bd88e3350479b29646b37b67316026c52a05a3a769c902f6f9c06a0ca4e3"},"schema_version":"1.0"},"canonical_sha256":"a4667a2d575e8a658e133d92c0b4c0ca34d1370b6122b59d903850e3b38820b3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:25:09.728014Z","signature_b64":"c4iWm+Yb1ZWIwj5DrT4lX4q5m3V0B8ySfwOhX+yKESiPqOi9eRZX0/yo/tvLT4OUe41WIgzBKDeMAZIQSfOICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4667a2d575e8a658e133d92c0b4c0ca34d1370b6122b59d903850e3b38820b3","last_reissued_at":"2026-07-05T02:25:09.727563Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:25:09.727563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2001.05411","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:25:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fg4At0LbRDYrSIWMaa4GKgNA0Km2+nsGMA3eT7+vweg4VgRRCCBi/XFp+fjynE4FtQmXyhx/I4yNHA8c9WAXAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T02:54:56.914232Z"},"content_sha256":"6f2a0d81b2074c59891a9c9e4f89f16e6cdfa26de5e0ba1d4ec137c0b49fff2a","schema_version":"1.0","event_id":"sha256:6f2a0d81b2074c59891a9c9e4f89f16e6cdfa26de5e0ba1d4ec137c0b49fff2a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:URTHULKXL2FGLDQTHWJMBNGAZI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lipschitz Lifelong Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Abel, Emmanuel Rachelson, Erwan Lecarpentier, Kavosh Asadi, Michael L. Littman, Yuu Jinnai","submitted_at":"2020-01-15T16:29:30Z","abstract_excerpt":"We consider the problem of knowledge transfer when an agent is facing a series of Reinforcement Learning (RL) tasks. We introduce a novel metric between Markov Decision Processes (MDPs) and establish that close MDPs have close optimal value functions. Formally, the optimal value functions are Lipschitz continuous with respect to the tasks space. These theoretical results lead us to a value-transfer method for Lifelong RL, which we use to build a PAC-MDP algorithm with improved convergence rate. Further, we show the method to experience no negative transfer with high probability. We illustrate "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.05411","kind":"arxiv","version":3},"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/2001.05411/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":"2026-07-05T02:25:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zGlkKGx9HXFCdGuMSGcAVwVNQ10lnUiO0DhUQFt5E9Ptu8eFJ0OUai5ElVXeJpidkxz1+G4frbKDQepEZ+wTAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T02:54:56.915007Z"},"content_sha256":"36b3362a8fa6e4de08fcdab456ee650bcca4e84417724f085fe4ebb42c9c4d3c","schema_version":"1.0","event_id":"sha256:36b3362a8fa6e4de08fcdab456ee650bcca4e84417724f085fe4ebb42c9c4d3c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/URTHULKXL2FGLDQTHWJMBNGAZI/bundle.json","state_url":"https://pith.science/pith/URTHULKXL2FGLDQTHWJMBNGAZI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/URTHULKXL2FGLDQTHWJMBNGAZI/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":"2026-08-11T02:54:56Z","links":{"resolver":"https://pith.science/pith/URTHULKXL2FGLDQTHWJMBNGAZI","bundle":"https://pith.science/pith/URTHULKXL2FGLDQTHWJMBNGAZI/bundle.json","state":"https://pith.science/pith/URTHULKXL2FGLDQTHWJMBNGAZI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/URTHULKXL2FGLDQTHWJMBNGAZI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:URTHULKXL2FGLDQTHWJMBNGAZI","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":"8072bd88e3350479b29646b37b67316026c52a05a3a769c902f6f9c06a0ca4e3","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-15T16:29:30Z","title_canon_sha256":"0c699763278e595d5ecf6dc374c2d4cf94638a669971311095bda7028131a298"},"schema_version":"1.0","source":{"id":"2001.05411","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.05411","created_at":"2026-07-05T02:25:09Z"},{"alias_kind":"arxiv_version","alias_value":"2001.05411v3","created_at":"2026-07-05T02:25:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.05411","created_at":"2026-07-05T02:25:09Z"},{"alias_kind":"pith_short_12","alias_value":"URTHULKXL2FG","created_at":"2026-07-05T02:25:09Z"},{"alias_kind":"pith_short_16","alias_value":"URTHULKXL2FGLDQT","created_at":"2026-07-05T02:25:09Z"},{"alias_kind":"pith_short_8","alias_value":"URTHULKX","created_at":"2026-07-05T02:25:09Z"}],"graph_snapshots":[{"event_id":"sha256:36b3362a8fa6e4de08fcdab456ee650bcca4e84417724f085fe4ebb42c9c4d3c","target":"graph","created_at":"2026-07-05T02:25:09Z","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/2001.05411/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the problem of knowledge transfer when an agent is facing a series of Reinforcement Learning (RL) tasks. We introduce a novel metric between Markov Decision Processes (MDPs) and establish that close MDPs have close optimal value functions. Formally, the optimal value functions are Lipschitz continuous with respect to the tasks space. These theoretical results lead us to a value-transfer method for Lifelong RL, which we use to build a PAC-MDP algorithm with improved convergence rate. Further, we show the method to experience no negative transfer with high probability. We illustrate ","authors_text":"David Abel, Emmanuel Rachelson, Erwan Lecarpentier, Kavosh Asadi, Michael L. Littman, Yuu Jinnai","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-15T16:29:30Z","title":"Lipschitz Lifelong Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.05411","kind":"arxiv","version":3},"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":"sha256:6f2a0d81b2074c59891a9c9e4f89f16e6cdfa26de5e0ba1d4ec137c0b49fff2a","target":"record","created_at":"2026-07-05T02:25:09Z","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":"8072bd88e3350479b29646b37b67316026c52a05a3a769c902f6f9c06a0ca4e3","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-15T16:29:30Z","title_canon_sha256":"0c699763278e595d5ecf6dc374c2d4cf94638a669971311095bda7028131a298"},"schema_version":"1.0","source":{"id":"2001.05411","kind":"arxiv","version":3}},"canonical_sha256":"a4667a2d575e8a658e133d92c0b4c0ca34d1370b6122b59d903850e3b38820b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a4667a2d575e8a658e133d92c0b4c0ca34d1370b6122b59d903850e3b38820b3","first_computed_at":"2026-07-05T02:25:09.727563Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:25:09.727563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c4iWm+Yb1ZWIwj5DrT4lX4q5m3V0B8ySfwOhX+yKESiPqOi9eRZX0/yo/tvLT4OUe41WIgzBKDeMAZIQSfOICw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:25:09.728014Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.05411","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f2a0d81b2074c59891a9c9e4f89f16e6cdfa26de5e0ba1d4ec137c0b49fff2a","sha256:36b3362a8fa6e4de08fcdab456ee650bcca4e84417724f085fe4ebb42c9c4d3c"],"state_sha256":"d75c6a3457df9100534e8c4888cc7b9ba79dc0f3252c71f8c26eb25a46a06009"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Z8c7BvFw5p19bCM/p9f98ZoBuHcpXYfn2qKGi8WfdbKRyEiTMr3OuBr/0v4XFG6U4QTjFiqSn5mBozrT4UCCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T02:54:56.920585Z","bundle_sha256":"754d8191e8fa9965efdd321e5816eaf00986fcba5d035ec55127462d6015cdb2"}}