{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PKVN3R5EMX4Q7YH7VGVGLBBQYX","short_pith_number":"pith:PKVN3R5E","schema_version":"1.0","canonical_sha256":"7aaaddc7a465f90fe0ffa9aa658430c5c5ab3d0fad22cf784edc479bf924a885","source":{"kind":"arxiv","id":"2101.07599","version":1},"attestation_state":"computed","paper":{"title":"Meta-Reinforcement Learning for Adaptive Motor Control in Changing Robot Dynamics and Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Jack Wilkinson, Timoth\\'ee Anne, Zhibin Li","submitted_at":"2021-01-19T12:57:12Z","abstract_excerpt":"This work developed a meta-learning approach that adapts the control policy on the fly to different changing conditions for robust locomotion. The proposed method constantly updates the interaction model, samples feasible sequences of actions of estimated the state-action trajectories, and then applies the optimal actions to maximize the reward. To achieve online model adaptation, our proposed method learns different latent vectors of each training condition, which are selected online given the newly collected data. Our work designs appropriate state space and reward functions, and optimizes f"},"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":"2101.07599","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-01-19T12:57:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"00a915a0ff1908d8509fdff5ff2d7c6b35810e7d024d5fd1eb74b104b0ee0382","abstract_canon_sha256":"38938b3957473a21f3948399286938d819295946de37f5b5da73982ef3871bf0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:07:59.407054Z","signature_b64":"QwdrosVu9IkQSIDvAeeZk44vDQD5YLFIdZbeeCjIWPylDb7ObMgV4EFbnZcphUfoNT4v/M8vfhWjWECrAvW9Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7aaaddc7a465f90fe0ffa9aa658430c5c5ab3d0fad22cf784edc479bf924a885","last_reissued_at":"2026-07-05T02:07:59.406628Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:07:59.406628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-Reinforcement Learning for Adaptive Motor Control in Changing Robot Dynamics and Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Jack Wilkinson, Timoth\\'ee Anne, Zhibin Li","submitted_at":"2021-01-19T12:57:12Z","abstract_excerpt":"This work developed a meta-learning approach that adapts the control policy on the fly to different changing conditions for robust locomotion. The proposed method constantly updates the interaction model, samples feasible sequences of actions of estimated the state-action trajectories, and then applies the optimal actions to maximize the reward. To achieve online model adaptation, our proposed method learns different latent vectors of each training condition, which are selected online given the newly collected data. Our work designs appropriate state space and reward functions, and optimizes f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.07599","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/2101.07599/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":"2101.07599","created_at":"2026-07-05T02:07:59.406695+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.07599v1","created_at":"2026-07-05T02:07:59.406695+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.07599","created_at":"2026-07-05T02:07:59.406695+00:00"},{"alias_kind":"pith_short_12","alias_value":"PKVN3R5EMX4Q","created_at":"2026-07-05T02:07:59.406695+00:00"},{"alias_kind":"pith_short_16","alias_value":"PKVN3R5EMX4Q7YH7","created_at":"2026-07-05T02:07:59.406695+00:00"},{"alias_kind":"pith_short_8","alias_value":"PKVN3R5E","created_at":"2026-07-05T02:07:59.406695+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/PKVN3R5EMX4Q7YH7VGVGLBBQYX","json":"https://pith.science/pith/PKVN3R5EMX4Q7YH7VGVGLBBQYX.json","graph_json":"https://pith.science/api/pith-number/PKVN3R5EMX4Q7YH7VGVGLBBQYX/graph.json","events_json":"https://pith.science/api/pith-number/PKVN3R5EMX4Q7YH7VGVGLBBQYX/events.json","paper":"https://pith.science/paper/PKVN3R5E"},"agent_actions":{"view_html":"https://pith.science/pith/PKVN3R5EMX4Q7YH7VGVGLBBQYX","download_json":"https://pith.science/pith/PKVN3R5EMX4Q7YH7VGVGLBBQYX.json","view_paper":"https://pith.science/paper/PKVN3R5E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.07599&json=true","fetch_graph":"https://pith.science/api/pith-number/PKVN3R5EMX4Q7YH7VGVGLBBQYX/graph.json","fetch_events":"https://pith.science/api/pith-number/PKVN3R5EMX4Q7YH7VGVGLBBQYX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PKVN3R5EMX4Q7YH7VGVGLBBQYX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PKVN3R5EMX4Q7YH7VGVGLBBQYX/action/storage_attestation","attest_author":"https://pith.science/pith/PKVN3R5EMX4Q7YH7VGVGLBBQYX/action/author_attestation","sign_citation":"https://pith.science/pith/PKVN3R5EMX4Q7YH7VGVGLBBQYX/action/citation_signature","submit_replication":"https://pith.science/pith/PKVN3R5EMX4Q7YH7VGVGLBBQYX/action/replication_record"}},"created_at":"2026-07-05T02:07:59.406695+00:00","updated_at":"2026-07-05T02:07:59.406695+00:00"}