{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:LYM5INWWJPH5M7BBOYYEIALDLG","short_pith_number":"pith:LYM5INWW","schema_version":"1.0","canonical_sha256":"5e19d436d64bcfd67c21763044016359ab1c2cd40d25bbe578f6303c2e935e3e","source":{"kind":"arxiv","id":"1703.02949","version":1},"attestation_state":"computed","paper":{"title":"Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Abhishek Gupta, Coline Devin, Pieter Abbeel, Sergey Levine, Yuxuan Liu","submitted_at":"2017-03-08T18:09:32Z","abstract_excerpt":"People can learn a wide range of tasks from their own experience, but can also learn from observing other creatures. This can accelerate acquisition of new skills even when the observed agent differs substantially from the learning agent in terms of morphology. In this paper, we examine how reinforcement learning algorithms can transfer knowledge between morphologically different agents (e.g., different robots). We introduce a problem formulation where two agents are tasked with learning multiple skills by sharing information. Our method uses the skills that were learned by both agents to trai"},"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":"1703.02949","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-08T18:09:32Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"9a199f4051108558b5f1ec811ac410a678bcaa12073a49372046bda79fc9bb53","abstract_canon_sha256":"155a9a2e242c3e03916b292a619e0c096e87b9ec191eaf44215cf971e94dc3ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:05.237131Z","signature_b64":"MBmAEoOrpvfEQMUIt/QiWQV/XWMsAs8IeUKHpIKXK+psMwRkxHpWtpUYWk3a9vrp7HbAeIdXp9FHZo9IK5RvAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e19d436d64bcfd67c21763044016359ab1c2cd40d25bbe578f6303c2e935e3e","last_reissued_at":"2026-05-18T00:49:05.236678Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:05.236678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Abhishek Gupta, Coline Devin, Pieter Abbeel, Sergey Levine, Yuxuan Liu","submitted_at":"2017-03-08T18:09:32Z","abstract_excerpt":"People can learn a wide range of tasks from their own experience, but can also learn from observing other creatures. This can accelerate acquisition of new skills even when the observed agent differs substantially from the learning agent in terms of morphology. In this paper, we examine how reinforcement learning algorithms can transfer knowledge between morphologically different agents (e.g., different robots). We introduce a problem formulation where two agents are tasked with learning multiple skills by sharing information. Our method uses the skills that were learned by both agents to trai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.02949","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":""},"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":"1703.02949","created_at":"2026-05-18T00:49:05.236745+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.02949v1","created_at":"2026-05-18T00:49:05.236745+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.02949","created_at":"2026-05-18T00:49:05.236745+00:00"},{"alias_kind":"pith_short_12","alias_value":"LYM5INWWJPH5","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"LYM5INWWJPH5M7BB","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"LYM5INWW","created_at":"2026-05-18T12:31:28.150371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"1907.02874","citing_title":"Attentive Multi-Task Deep Reinforcement Learning","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"1907.11740","citing_title":"Environment Probing Interaction Policies","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20811","citing_title":"Demo-JEPA: Joint-Embedding Predictive Architecture for One-shot Cross-Embodiment Imitation","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"1910.11215","citing_title":"RoboNet: Large-Scale Multi-Robot Learning","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"1910.07113","citing_title":"Solving Rubik's Cube with a Robot Hand","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LYM5INWWJPH5M7BBOYYEIALDLG","json":"https://pith.science/pith/LYM5INWWJPH5M7BBOYYEIALDLG.json","graph_json":"https://pith.science/api/pith-number/LYM5INWWJPH5M7BBOYYEIALDLG/graph.json","events_json":"https://pith.science/api/pith-number/LYM5INWWJPH5M7BBOYYEIALDLG/events.json","paper":"https://pith.science/paper/LYM5INWW"},"agent_actions":{"view_html":"https://pith.science/pith/LYM5INWWJPH5M7BBOYYEIALDLG","download_json":"https://pith.science/pith/LYM5INWWJPH5M7BBOYYEIALDLG.json","view_paper":"https://pith.science/paper/LYM5INWW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.02949&json=true","fetch_graph":"https://pith.science/api/pith-number/LYM5INWWJPH5M7BBOYYEIALDLG/graph.json","fetch_events":"https://pith.science/api/pith-number/LYM5INWWJPH5M7BBOYYEIALDLG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LYM5INWWJPH5M7BBOYYEIALDLG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LYM5INWWJPH5M7BBOYYEIALDLG/action/storage_attestation","attest_author":"https://pith.science/pith/LYM5INWWJPH5M7BBOYYEIALDLG/action/author_attestation","sign_citation":"https://pith.science/pith/LYM5INWWJPH5M7BBOYYEIALDLG/action/citation_signature","submit_replication":"https://pith.science/pith/LYM5INWWJPH5M7BBOYYEIALDLG/action/replication_record"}},"created_at":"2026-05-18T00:49:05.236745+00:00","updated_at":"2026-05-18T00:49:05.236745+00:00"}