{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:VI2NTZVD3R4HONNGAFI5VKK2WL","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":"6775bd3d9445d2ad0186d8319265313ded198b300f38d9d955a25728401288c4","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-08T22:12:59Z","title_canon_sha256":"c7fa85e80e5bf22d346a166f4af8f90339031a4c67c685d5eec742a591e21ed0"},"schema_version":"1.0","source":{"id":"2002.03240","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.03240","created_at":"2026-07-05T01:57:14Z"},{"alias_kind":"arxiv_version","alias_value":"2002.03240v3","created_at":"2026-07-05T01:57:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.03240","created_at":"2026-07-05T01:57:14Z"},{"alias_kind":"pith_short_12","alias_value":"VI2NTZVD3R4H","created_at":"2026-07-05T01:57:14Z"},{"alias_kind":"pith_short_16","alias_value":"VI2NTZVD3R4HONNG","created_at":"2026-07-05T01:57:14Z"},{"alias_kind":"pith_short_8","alias_value":"VI2NTZVD","created_at":"2026-07-05T01:57:14Z"}],"graph_snapshots":[{"event_id":"sha256:fe28d9c585362ca712280fe2b5dda3e78ced4162c94e2de76cb07335dca59785","target":"graph","created_at":"2026-07-05T01:57:14Z","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/2002.03240/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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.","authors_text":"Fran\\c{c}ois Fleuret, Karthigan Sinnathamby, Vincent Micheli","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-08T22:12:59Z","title":"Multi-task Reinforcement Learning with a Planning Quasi-Metric"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.03240","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":"sha256:08a375f9ffffe2560b96201e8930dd13def22a5e08737406a9d751c24a62dda7","target":"record","created_at":"2026-07-05T01:57:14Z","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":"6775bd3d9445d2ad0186d8319265313ded198b300f38d9d955a25728401288c4","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-08T22:12:59Z","title_canon_sha256":"c7fa85e80e5bf22d346a166f4af8f90339031a4c67c685d5eec742a591e21ed0"},"schema_version":"1.0","source":{"id":"2002.03240","kind":"arxiv","version":3}},"canonical_sha256":"aa34d9e6a3dc787735a60151daa95ab2ddfe5407d138c94b9c346ae65ba5b32f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa34d9e6a3dc787735a60151daa95ab2ddfe5407d138c94b9c346ae65ba5b32f","first_computed_at":"2026-07-05T01:57:14.583601Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:57:14.583601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9V9xRmt6YW1+h012uk1kc1MJZxjMVg3qUUe+hrBT41tefxMIkKuFsZ0JOhikOeQygd1QEfXVgWNNVM1+28NKAg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:57:14.584004Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.03240","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08a375f9ffffe2560b96201e8930dd13def22a5e08737406a9d751c24a62dda7","sha256:fe28d9c585362ca712280fe2b5dda3e78ced4162c94e2de76cb07335dca59785"],"state_sha256":"47f7cbc639344e139fde49097020b08892a70dc79f80739d1bdadc7fd8d36c08"}