{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7WB6D7GTODWL6YAY6P3LHFAXOR","short_pith_number":"pith:7WB6D7GT","schema_version":"1.0","canonical_sha256":"fd83e1fcd370ecbf6018f3f6b394177456ff1f9e1f132da836fec24543eb03ac","source":{"kind":"arxiv","id":"1908.05265","version":2},"attestation_state":"computed","paper":{"title":"Skill Transfer in Deep Reinforcement Learning under Morphological Heterogeneity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Giovanni Montana, Yang Hu","submitted_at":"2019-08-14T17:42:43Z","abstract_excerpt":"Transfer learning methods for reinforcement learning (RL) domains facilitate the acquisition of new skills using previously acquired knowledge. The vast majority of existing approaches assume that the agents have the same design, e.g. same shape and action spaces. In this paper we address the problem of transferring previously acquired skills amongst morphologically different agents (MDAs). For instance, assuming that a bipedal agent has been trained to move forward, could this skill be transferred on to a one-leg hopper so as to make its training process for the same task more sample efficien"},"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":"1908.05265","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-14T17:42:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"928f04e28d2913da7a40976383ac222f2568991c6999f362e735ed0f4536559a","abstract_canon_sha256":"5fda4a79ecfa0c90ddf9750274d3ac4ce4a73dff559726211616bb8962e44dd9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:58:29.081424Z","signature_b64":"oHMxFjS4mfiDX7UePfiUkkvKgvQ2nFi0uStSlq6XpLvrRjZvAWQKDLVl9qhSvb867Qz+VPTiMsRvOWh9Sd/nBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd83e1fcd370ecbf6018f3f6b394177456ff1f9e1f132da836fec24543eb03ac","last_reissued_at":"2026-07-04T23:58:29.080971Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:58:29.080971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Skill Transfer in Deep Reinforcement Learning under Morphological Heterogeneity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Giovanni Montana, Yang Hu","submitted_at":"2019-08-14T17:42:43Z","abstract_excerpt":"Transfer learning methods for reinforcement learning (RL) domains facilitate the acquisition of new skills using previously acquired knowledge. The vast majority of existing approaches assume that the agents have the same design, e.g. same shape and action spaces. In this paper we address the problem of transferring previously acquired skills amongst morphologically different agents (MDAs). For instance, assuming that a bipedal agent has been trained to move forward, could this skill be transferred on to a one-leg hopper so as to make its training process for the same task more sample efficien"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.05265","kind":"arxiv","version":2},"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/1908.05265/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":"1908.05265","created_at":"2026-07-04T23:58:29.081028+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.05265v2","created_at":"2026-07-04T23:58:29.081028+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.05265","created_at":"2026-07-04T23:58:29.081028+00:00"},{"alias_kind":"pith_short_12","alias_value":"7WB6D7GTODWL","created_at":"2026-07-04T23:58:29.081028+00:00"},{"alias_kind":"pith_short_16","alias_value":"7WB6D7GTODWL6YAY","created_at":"2026-07-04T23:58:29.081028+00:00"},{"alias_kind":"pith_short_8","alias_value":"7WB6D7GT","created_at":"2026-07-04T23:58:29.081028+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.18780","citing_title":"DreamPolicy: A Unified World-model Policy for Scalable Humanoid Locomotion","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7WB6D7GTODWL6YAY6P3LHFAXOR","json":"https://pith.science/pith/7WB6D7GTODWL6YAY6P3LHFAXOR.json","graph_json":"https://pith.science/api/pith-number/7WB6D7GTODWL6YAY6P3LHFAXOR/graph.json","events_json":"https://pith.science/api/pith-number/7WB6D7GTODWL6YAY6P3LHFAXOR/events.json","paper":"https://pith.science/paper/7WB6D7GT"},"agent_actions":{"view_html":"https://pith.science/pith/7WB6D7GTODWL6YAY6P3LHFAXOR","download_json":"https://pith.science/pith/7WB6D7GTODWL6YAY6P3LHFAXOR.json","view_paper":"https://pith.science/paper/7WB6D7GT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.05265&json=true","fetch_graph":"https://pith.science/api/pith-number/7WB6D7GTODWL6YAY6P3LHFAXOR/graph.json","fetch_events":"https://pith.science/api/pith-number/7WB6D7GTODWL6YAY6P3LHFAXOR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7WB6D7GTODWL6YAY6P3LHFAXOR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7WB6D7GTODWL6YAY6P3LHFAXOR/action/storage_attestation","attest_author":"https://pith.science/pith/7WB6D7GTODWL6YAY6P3LHFAXOR/action/author_attestation","sign_citation":"https://pith.science/pith/7WB6D7GTODWL6YAY6P3LHFAXOR/action/citation_signature","submit_replication":"https://pith.science/pith/7WB6D7GTODWL6YAY6P3LHFAXOR/action/replication_record"}},"created_at":"2026-07-04T23:58:29.081028+00:00","updated_at":"2026-07-04T23:58:29.081028+00:00"}