{"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"}