{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:JKAQN5Y2NDEDXSTMSJWVY3N5XU","short_pith_number":"pith:JKAQN5Y2","schema_version":"1.0","canonical_sha256":"4a8106f71a68c83bca6c926d5c6dbdbd09dde4b55cd87d03d98e8b97319e4d5c","source":{"kind":"arxiv","id":"2010.11944","version":1},"attestation_state":"computed","paper":{"title":"Accelerating Reinforcement Learning with Learned Skill Priors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Joseph J. Lim, Karl Pertsch, Youngwoon Lee","submitted_at":"2020-10-22T17:59:51Z","abstract_excerpt":"Intelligent agents rely heavily on prior experience when learning a new task, yet most modern reinforcement learning (RL) approaches learn every task from scratch. One approach for leveraging prior knowledge is to transfer skills learned on prior tasks to the new task. However, as the amount of prior experience increases, the number of transferable skills grows too, making it challenging to explore the full set of available skills during downstream learning. Yet, intuitively, not all skills should be explored with equal probability; for example information about the current state can hint whic"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2010.11944","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-22T17:59:51Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"530ba4c4dc3543aa501ea8ee5405b284dbb8bbcbe41dba5dd2ce251df0ee235e","abstract_canon_sha256":"3f5d06611f45841bc395214f0b3c8bbc31494411542ae96744578f7835b45d73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:22.353094Z","signature_b64":"3z4/dTcjMjtxavijj3R8l0gg9P/RfQdq1OKLXGwHnK64tQKTUdSgPtQSbpkNLR4PUuieMALSbFXh8tZOMwxTAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a8106f71a68c83bca6c926d5c6dbdbd09dde4b55cd87d03d98e8b97319e4d5c","last_reissued_at":"2026-07-05T01:45:22.352745Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:22.352745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerating Reinforcement Learning with Learned Skill Priors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Joseph J. Lim, Karl Pertsch, Youngwoon Lee","submitted_at":"2020-10-22T17:59:51Z","abstract_excerpt":"Intelligent agents rely heavily on prior experience when learning a new task, yet most modern reinforcement learning (RL) approaches learn every task from scratch. One approach for leveraging prior knowledge is to transfer skills learned on prior tasks to the new task. However, as the amount of prior experience increases, the number of transferable skills grows too, making it challenging to explore the full set of available skills during downstream learning. Yet, intuitively, not all skills should be explored with equal probability; for example information about the current state can hint whic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.11944","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/2010.11944/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2010.11944","created_at":"2026-07-05T01:45:22.352800+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.11944v1","created_at":"2026-07-05T01:45:22.352800+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.11944","created_at":"2026-07-05T01:45:22.352800+00:00"},{"alias_kind":"pith_short_12","alias_value":"JKAQN5Y2NDED","created_at":"2026-07-05T01:45:22.352800+00:00"},{"alias_kind":"pith_short_16","alias_value":"JKAQN5Y2NDEDXSTM","created_at":"2026-07-05T01:45:22.352800+00:00"},{"alias_kind":"pith_short_8","alias_value":"JKAQN5Y2","created_at":"2026-07-05T01:45:22.352800+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06323","citing_title":"LAMP: Latent Motion Prior-Guided Real-World Learning for Dexterous Hand Manipulation","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2106.01345","citing_title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2108.03298","citing_title":"What Matters in Learning from Offline Human Demonstrations for Robot Manipulation","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26689","citing_title":"Atomic-Probe Governance for Skill Updates in Compositional Robot Policies","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26689","citing_title":"Atomic-Probe Governance for Skill Updates in Compositional Robot Policies","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08059","citing_title":"Governed Capability Evolution: Lifecycle-Time Compatibility Checking and Rollback for AI-Component-Based Systems, with Embodied Agents as Case Study","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08059","citing_title":"Governed Capability Evolution: Lifecycle-Time Compatibility Checking and Rollback for AI-Component-Based Systems, with Embodied Agents as Case Study","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JKAQN5Y2NDEDXSTMSJWVY3N5XU","json":"https://pith.science/pith/JKAQN5Y2NDEDXSTMSJWVY3N5XU.json","graph_json":"https://pith.science/api/pith-number/JKAQN5Y2NDEDXSTMSJWVY3N5XU/graph.json","events_json":"https://pith.science/api/pith-number/JKAQN5Y2NDEDXSTMSJWVY3N5XU/events.json","paper":"https://pith.science/paper/JKAQN5Y2"},"agent_actions":{"view_html":"https://pith.science/pith/JKAQN5Y2NDEDXSTMSJWVY3N5XU","download_json":"https://pith.science/pith/JKAQN5Y2NDEDXSTMSJWVY3N5XU.json","view_paper":"https://pith.science/paper/JKAQN5Y2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.11944&json=true","fetch_graph":"https://pith.science/api/pith-number/JKAQN5Y2NDEDXSTMSJWVY3N5XU/graph.json","fetch_events":"https://pith.science/api/pith-number/JKAQN5Y2NDEDXSTMSJWVY3N5XU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JKAQN5Y2NDEDXSTMSJWVY3N5XU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JKAQN5Y2NDEDXSTMSJWVY3N5XU/action/storage_attestation","attest_author":"https://pith.science/pith/JKAQN5Y2NDEDXSTMSJWVY3N5XU/action/author_attestation","sign_citation":"https://pith.science/pith/JKAQN5Y2NDEDXSTMSJWVY3N5XU/action/citation_signature","submit_replication":"https://pith.science/pith/JKAQN5Y2NDEDXSTMSJWVY3N5XU/action/replication_record"}},"created_at":"2026-07-05T01:45:22.352800+00:00","updated_at":"2026-07-05T01:45:22.352800+00:00"}