{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2PGFSDVNSJWRKDPGWDHJF3RDLS","short_pith_number":"pith:2PGFSDVN","schema_version":"1.0","canonical_sha256":"d3cc590ead926d150de6b0ce92ee235ca33e242c21ae7fedf148e178ec65069b","source":{"kind":"arxiv","id":"2309.12529","version":1},"attestation_state":"computed","paper":{"title":"Curriculum Reinforcement Learning via Morphology-Environment Co-Evolution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Guodong Long, Jing Jiang, Shuang Ao, Tianyi Zhou, Xuan Song","submitted_at":"2023-09-21T22:58:59Z","abstract_excerpt":"Throughout long history, natural species have learned to survive by evolving their physical structures adaptive to the environment changes. In contrast, current reinforcement learning (RL) studies mainly focus on training an agent with a fixed morphology (e.g., skeletal structure and joint attributes) in a fixed environment, which can hardly generalize to changing environments or new tasks. In this paper, we optimize an RL agent and its morphology through ``morphology-environment co-evolution (MECE)'', in which the morphology keeps being updated to adapt to the changing environment, while the "},"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":"2309.12529","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-09-21T22:58:59Z","cross_cats_sorted":[],"title_canon_sha256":"ec5ffe2b0b863dd7a40bae3bbc72fdae527ac068576ea8f4b34e8dce943c8763","abstract_canon_sha256":"4b64e50ab0d0496fda2ab8e9caeeed931011239a3b9fedc3bb126a8eb643ef17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:53:13.956602Z","signature_b64":"K4l6n/bh9EPBuIkxETtoe0Y9zWBXydjDFkaZp7PUjAQjFhOrZq4x8+MpaWbfzd3DVI5pMw+L5RZH77GhE9OuBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3cc590ead926d150de6b0ce92ee235ca33e242c21ae7fedf148e178ec65069b","last_reissued_at":"2026-07-05T06:53:13.956110Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:53:13.956110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Curriculum Reinforcement Learning via Morphology-Environment Co-Evolution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Guodong Long, Jing Jiang, Shuang Ao, Tianyi Zhou, Xuan Song","submitted_at":"2023-09-21T22:58:59Z","abstract_excerpt":"Throughout long history, natural species have learned to survive by evolving their physical structures adaptive to the environment changes. In contrast, current reinforcement learning (RL) studies mainly focus on training an agent with a fixed morphology (e.g., skeletal structure and joint attributes) in a fixed environment, which can hardly generalize to changing environments or new tasks. In this paper, we optimize an RL agent and its morphology through ``morphology-environment co-evolution (MECE)'', in which the morphology keeps being updated to adapt to the changing environment, while the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.12529","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/2309.12529/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":"2309.12529","created_at":"2026-07-05T06:53:13.956169+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.12529v1","created_at":"2026-07-05T06:53:13.956169+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.12529","created_at":"2026-07-05T06:53:13.956169+00:00"},{"alias_kind":"pith_short_12","alias_value":"2PGFSDVNSJWR","created_at":"2026-07-05T06:53:13.956169+00:00"},{"alias_kind":"pith_short_16","alias_value":"2PGFSDVNSJWRKDPG","created_at":"2026-07-05T06:53:13.956169+00:00"},{"alias_kind":"pith_short_8","alias_value":"2PGFSDVN","created_at":"2026-07-05T06:53:13.956169+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02771","citing_title":"Grounding Intelligence in Movement","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2PGFSDVNSJWRKDPGWDHJF3RDLS","json":"https://pith.science/pith/2PGFSDVNSJWRKDPGWDHJF3RDLS.json","graph_json":"https://pith.science/api/pith-number/2PGFSDVNSJWRKDPGWDHJF3RDLS/graph.json","events_json":"https://pith.science/api/pith-number/2PGFSDVNSJWRKDPGWDHJF3RDLS/events.json","paper":"https://pith.science/paper/2PGFSDVN"},"agent_actions":{"view_html":"https://pith.science/pith/2PGFSDVNSJWRKDPGWDHJF3RDLS","download_json":"https://pith.science/pith/2PGFSDVNSJWRKDPGWDHJF3RDLS.json","view_paper":"https://pith.science/paper/2PGFSDVN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.12529&json=true","fetch_graph":"https://pith.science/api/pith-number/2PGFSDVNSJWRKDPGWDHJF3RDLS/graph.json","fetch_events":"https://pith.science/api/pith-number/2PGFSDVNSJWRKDPGWDHJF3RDLS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2PGFSDVNSJWRKDPGWDHJF3RDLS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2PGFSDVNSJWRKDPGWDHJF3RDLS/action/storage_attestation","attest_author":"https://pith.science/pith/2PGFSDVNSJWRKDPGWDHJF3RDLS/action/author_attestation","sign_citation":"https://pith.science/pith/2PGFSDVNSJWRKDPGWDHJF3RDLS/action/citation_signature","submit_replication":"https://pith.science/pith/2PGFSDVNSJWRKDPGWDHJF3RDLS/action/replication_record"}},"created_at":"2026-07-05T06:53:13.956169+00:00","updated_at":"2026-07-05T06:53:13.956169+00:00"}