{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:6Q7NBQORURDEYMR47HFJFBKXKL","short_pith_number":"pith:6Q7NBQOR","canonical_record":{"source":{"id":"2012.03548","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-07T09:33:02Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"4ba0825d107de3013af3ee479a3f3fec5cf62773e8c863fc9a0eb3d062cf138c","abstract_canon_sha256":"8b6b6711fe938d7243d3d8cc9ba2a716b494378826078b0128910d03373aee58"},"schema_version":"1.0"},"canonical_sha256":"f43ed0c1d1a4464c323cf9ca92855752e2d4c69133a7b196bbdcf3ee6f93d40f","source":{"kind":"arxiv","id":"2012.03548","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.03548","created_at":"2026-07-05T02:49:51Z"},{"alias_kind":"arxiv_version","alias_value":"2012.03548v3","created_at":"2026-07-05T02:49:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.03548","created_at":"2026-07-05T02:49:51Z"},{"alias_kind":"pith_short_12","alias_value":"6Q7NBQORURDE","created_at":"2026-07-05T02:49:51Z"},{"alias_kind":"pith_short_16","alias_value":"6Q7NBQORURDEYMR4","created_at":"2026-07-05T02:49:51Z"},{"alias_kind":"pith_short_8","alias_value":"6Q7NBQOR","created_at":"2026-07-05T02:49:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:6Q7NBQORURDEYMR47HFJFBKXKL","target":"record","payload":{"canonical_record":{"source":{"id":"2012.03548","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-07T09:33:02Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"4ba0825d107de3013af3ee479a3f3fec5cf62773e8c863fc9a0eb3d062cf138c","abstract_canon_sha256":"8b6b6711fe938d7243d3d8cc9ba2a716b494378826078b0128910d03373aee58"},"schema_version":"1.0"},"canonical_sha256":"f43ed0c1d1a4464c323cf9ca92855752e2d4c69133a7b196bbdcf3ee6f93d40f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:49:51.960089Z","signature_b64":"u/PCgfl4kEEr2gZd8qlB/oGZAsNWNf76Ce0oE5gKsrk//MiN7Za6eWpqh0HvRJdmaha2VxDpQwemJBzbzBq7Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f43ed0c1d1a4464c323cf9ca92855752e2d4c69133a7b196bbdcf3ee6f93d40f","last_reissued_at":"2026-07-05T02:49:51.959608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:49:51.959608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.03548","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":"2026-07-05T02:49:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ES9z1iaAKZZkz9CvWubeTCLDNkEkAzUPDVOzdizJys+x8QeR7jy3lTkvt5PdBt1mbgPqVArneV+++EAnGY+oCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T20:56:26.412202Z"},"content_sha256":"61ebecdda47025850c59af162e2563afffc383d5c51f989f4da0d3cd702f23db","schema_version":"1.0","event_id":"sha256:61ebecdda47025850c59af162e2563afffc383d5c51f989f4da0d3cd702f23db"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:6Q7NBQORURDEYMR47HFJFBKXKL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reset-Free Lifelong Learning with Skill-Space Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Aditya Grover, Igor Mordatch, Kevin Lu, Pieter Abbeel","submitted_at":"2020-12-07T09:33:02Z","abstract_excerpt":"The objective of lifelong reinforcement learning (RL) is to optimize agents which can continuously adapt and interact in changing environments. However, current RL approaches fail drastically when environments are non-stationary and interactions are non-episodic. We propose Lifelong Skill Planning (LiSP), an algorithmic framework for non-episodic lifelong RL based on planning in an abstract space of higher-order skills. We learn the skills in an unsupervised manner using intrinsic rewards and plan over the learned skills using a learned dynamics model. Moreover, our framework permits skill dis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.03548","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/2012.03548/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":"2026-07-05T02:49:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I3ZmpotU4G42xlKZubEBFp7YHmo/BdTfy/KxHeKkpbBy5ObGz1jTauIJ+yA7rser+KXxiCmf/bOF0BqsBsn5DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T20:56:26.414307Z"},"content_sha256":"8dbd6fe05e64cd403f275ff8a3aac3b66582fd19335729fcdd3b05343904dd93","schema_version":"1.0","event_id":"sha256:8dbd6fe05e64cd403f275ff8a3aac3b66582fd19335729fcdd3b05343904dd93"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6Q7NBQORURDEYMR47HFJFBKXKL/bundle.json","state_url":"https://pith.science/pith/6Q7NBQORURDEYMR47HFJFBKXKL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6Q7NBQORURDEYMR47HFJFBKXKL/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":"2026-08-16T20:56:26Z","links":{"resolver":"https://pith.science/pith/6Q7NBQORURDEYMR47HFJFBKXKL","bundle":"https://pith.science/pith/6Q7NBQORURDEYMR47HFJFBKXKL/bundle.json","state":"https://pith.science/pith/6Q7NBQORURDEYMR47HFJFBKXKL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6Q7NBQORURDEYMR47HFJFBKXKL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:6Q7NBQORURDEYMR47HFJFBKXKL","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":"8b6b6711fe938d7243d3d8cc9ba2a716b494378826078b0128910d03373aee58","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-07T09:33:02Z","title_canon_sha256":"4ba0825d107de3013af3ee479a3f3fec5cf62773e8c863fc9a0eb3d062cf138c"},"schema_version":"1.0","source":{"id":"2012.03548","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.03548","created_at":"2026-07-05T02:49:51Z"},{"alias_kind":"arxiv_version","alias_value":"2012.03548v3","created_at":"2026-07-05T02:49:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.03548","created_at":"2026-07-05T02:49:51Z"},{"alias_kind":"pith_short_12","alias_value":"6Q7NBQORURDE","created_at":"2026-07-05T02:49:51Z"},{"alias_kind":"pith_short_16","alias_value":"6Q7NBQORURDEYMR4","created_at":"2026-07-05T02:49:51Z"},{"alias_kind":"pith_short_8","alias_value":"6Q7NBQOR","created_at":"2026-07-05T02:49:51Z"}],"graph_snapshots":[{"event_id":"sha256:8dbd6fe05e64cd403f275ff8a3aac3b66582fd19335729fcdd3b05343904dd93","target":"graph","created_at":"2026-07-05T02:49:51Z","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/2012.03548/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The objective of lifelong reinforcement learning (RL) is to optimize agents which can continuously adapt and interact in changing environments. However, current RL approaches fail drastically when environments are non-stationary and interactions are non-episodic. We propose Lifelong Skill Planning (LiSP), an algorithmic framework for non-episodic lifelong RL based on planning in an abstract space of higher-order skills. We learn the skills in an unsupervised manner using intrinsic rewards and plan over the learned skills using a learned dynamics model. Moreover, our framework permits skill dis","authors_text":"Aditya Grover, Igor Mordatch, Kevin Lu, Pieter Abbeel","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-07T09:33:02Z","title":"Reset-Free Lifelong Learning with Skill-Space Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.03548","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":"sha256:61ebecdda47025850c59af162e2563afffc383d5c51f989f4da0d3cd702f23db","target":"record","created_at":"2026-07-05T02:49:51Z","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":"8b6b6711fe938d7243d3d8cc9ba2a716b494378826078b0128910d03373aee58","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-07T09:33:02Z","title_canon_sha256":"4ba0825d107de3013af3ee479a3f3fec5cf62773e8c863fc9a0eb3d062cf138c"},"schema_version":"1.0","source":{"id":"2012.03548","kind":"arxiv","version":3}},"canonical_sha256":"f43ed0c1d1a4464c323cf9ca92855752e2d4c69133a7b196bbdcf3ee6f93d40f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f43ed0c1d1a4464c323cf9ca92855752e2d4c69133a7b196bbdcf3ee6f93d40f","first_computed_at":"2026-07-05T02:49:51.959608Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:49:51.959608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u/PCgfl4kEEr2gZd8qlB/oGZAsNWNf76Ce0oE5gKsrk//MiN7Za6eWpqh0HvRJdmaha2VxDpQwemJBzbzBq7Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:49:51.960089Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.03548","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61ebecdda47025850c59af162e2563afffc383d5c51f989f4da0d3cd702f23db","sha256:8dbd6fe05e64cd403f275ff8a3aac3b66582fd19335729fcdd3b05343904dd93"],"state_sha256":"92f5583e22ba3887184de26369b2e89f6eeea65b49426662deca4c9c854d7d09"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1ixrAb3oTx6pH6Lr9TlMmbMENzT/Hi5OuOGBXKnDa8YxOyVnHeSZMbxU4KYtba1Z5r19aLk7MAxuGiseHY/XCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T20:56:26.423790Z","bundle_sha256":"82fc2f035c5cda011ec66820678a27aa42a83ccdb9a818b9e30456fcd15b734c"}}