{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:VI2NTZVD3R4HONNGAFI5VKK2WL","short_pith_number":"pith:VI2NTZVD","schema_version":"1.0","canonical_sha256":"aa34d9e6a3dc787735a60151daa95ab2ddfe5407d138c94b9c346ae65ba5b32f","source":{"kind":"arxiv","id":"2002.03240","version":3},"attestation_state":"computed","paper":{"title":"Multi-task Reinforcement Learning with a Planning Quasi-Metric","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Fran\\c{c}ois Fleuret, Karthigan Sinnathamby, Vincent Micheli","submitted_at":"2020-02-08T22:12:59Z","abstract_excerpt":"We introduce a new reinforcement learning approach combining a planning quasi-metric (PQM) that estimates the number of steps required to go from any state to another, with task-specific \"aimers\" that compute a target state to reach a given goal. This decomposition allows the sharing across tasks of a task-agnostic model of the quasi-metric that captures the environment's dynamics and can be learned in a dense and unsupervised manner. We achieve multiple-fold training speed-up compared to recently published methods on the standard bit-flip problem and in the MuJoCo robotic arm simulator."},"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":"2002.03240","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-08T22:12:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c7fa85e80e5bf22d346a166f4af8f90339031a4c67c685d5eec742a591e21ed0","abstract_canon_sha256":"6775bd3d9445d2ad0186d8319265313ded198b300f38d9d955a25728401288c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:57:14.584004Z","signature_b64":"9V9xRmt6YW1+h012uk1kc1MJZxjMVg3qUUe+hrBT41tefxMIkKuFsZ0JOhikOeQygd1QEfXVgWNNVM1+28NKAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa34d9e6a3dc787735a60151daa95ab2ddfe5407d138c94b9c346ae65ba5b32f","last_reissued_at":"2026-07-05T01:57:14.583601Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:57:14.583601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-task Reinforcement Learning with a Planning Quasi-Metric","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Fran\\c{c}ois Fleuret, Karthigan Sinnathamby, Vincent Micheli","submitted_at":"2020-02-08T22:12:59Z","abstract_excerpt":"We introduce a new reinforcement learning approach combining a planning quasi-metric (PQM) that estimates the number of steps required to go from any state to another, with task-specific \"aimers\" that compute a target state to reach a given goal. This decomposition allows the sharing across tasks of a task-agnostic model of the quasi-metric that captures the environment's dynamics and can be learned in a dense and unsupervised manner. We achieve multiple-fold training speed-up compared to recently published methods on the standard bit-flip problem and in the MuJoCo robotic arm simulator."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.03240","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/2002.03240/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":"2002.03240","created_at":"2026-07-05T01:57:14.583657+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.03240v3","created_at":"2026-07-05T01:57:14.583657+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.03240","created_at":"2026-07-05T01:57:14.583657+00:00"},{"alias_kind":"pith_short_12","alias_value":"VI2NTZVD3R4H","created_at":"2026-07-05T01:57:14.583657+00:00"},{"alias_kind":"pith_short_16","alias_value":"VI2NTZVD3R4HONNG","created_at":"2026-07-05T01:57:14.583657+00:00"},{"alias_kind":"pith_short_8","alias_value":"VI2NTZVD","created_at":"2026-07-05T01:57:14.583657+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VI2NTZVD3R4HONNGAFI5VKK2WL","json":"https://pith.science/pith/VI2NTZVD3R4HONNGAFI5VKK2WL.json","graph_json":"https://pith.science/api/pith-number/VI2NTZVD3R4HONNGAFI5VKK2WL/graph.json","events_json":"https://pith.science/api/pith-number/VI2NTZVD3R4HONNGAFI5VKK2WL/events.json","paper":"https://pith.science/paper/VI2NTZVD"},"agent_actions":{"view_html":"https://pith.science/pith/VI2NTZVD3R4HONNGAFI5VKK2WL","download_json":"https://pith.science/pith/VI2NTZVD3R4HONNGAFI5VKK2WL.json","view_paper":"https://pith.science/paper/VI2NTZVD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.03240&json=true","fetch_graph":"https://pith.science/api/pith-number/VI2NTZVD3R4HONNGAFI5VKK2WL/graph.json","fetch_events":"https://pith.science/api/pith-number/VI2NTZVD3R4HONNGAFI5VKK2WL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VI2NTZVD3R4HONNGAFI5VKK2WL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VI2NTZVD3R4HONNGAFI5VKK2WL/action/storage_attestation","attest_author":"https://pith.science/pith/VI2NTZVD3R4HONNGAFI5VKK2WL/action/author_attestation","sign_citation":"https://pith.science/pith/VI2NTZVD3R4HONNGAFI5VKK2WL/action/citation_signature","submit_replication":"https://pith.science/pith/VI2NTZVD3R4HONNGAFI5VKK2WL/action/replication_record"}},"created_at":"2026-07-05T01:57:14.583657+00:00","updated_at":"2026-07-05T01:57:14.583657+00:00"}