{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TRPBHHDGILRSSZGP4K2JUF66G5","short_pith_number":"pith:TRPBHHDG","schema_version":"1.0","canonical_sha256":"9c5e139c6642e32964cfe2b49a17de37454a5ad73ea1e173d2275c8a498f38fa","source":{"kind":"arxiv","id":"2209.10656","version":2},"attestation_state":"computed","paper":{"title":"Learning from Symmetry: Meta-Reinforcement Learning with Symmetrical Behaviors and Language Instructions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alois Knoll, Genghang Zhuang, Hongkuan Zhou, Kai Huang, Kejia Chen, Xiangtong Yao, Zhenshan Bing","submitted_at":"2022-09-21T20:54:21Z","abstract_excerpt":"Meta-reinforcement learning (meta-RL) is a promising approach that enables the agent to learn new tasks quickly. However, most meta-RL algorithms show poor generalization in multi-task scenarios due to the insufficient task information provided only by rewards. Language-conditioned meta-RL improves the generalization capability by matching language instructions with the agent's behaviors. While both behaviors and language instructions have symmetry, which can speed up human learning of new knowledge. Thus, combining symmetry and language instructions into meta-RL can help improve the algorithm"},"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":"2209.10656","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-09-21T20:54:21Z","cross_cats_sorted":[],"title_canon_sha256":"eabbdcb8356f5441c4fbfe40c6f1e64afb5031c04ffc0732747cd07cb9efb839","abstract_canon_sha256":"e2dfeb7d4106a215bb1581068baa3491fa1a35657ef483c9a3e46252fad80a76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:27:42.354076Z","signature_b64":"VylDGDd6bAyu8HGI/g/1KnUvDUPqHfZPAXQSDiNUe6BnjTG8vlZ+QKYsXHGd6T00jLZzHQGQqH08rP9aRl2eBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c5e139c6642e32964cfe2b49a17de37454a5ad73ea1e173d2275c8a498f38fa","last_reissued_at":"2026-07-05T06:27:42.353620Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:27:42.353620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning from Symmetry: Meta-Reinforcement Learning with Symmetrical Behaviors and Language Instructions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alois Knoll, Genghang Zhuang, Hongkuan Zhou, Kai Huang, Kejia Chen, Xiangtong Yao, Zhenshan Bing","submitted_at":"2022-09-21T20:54:21Z","abstract_excerpt":"Meta-reinforcement learning (meta-RL) is a promising approach that enables the agent to learn new tasks quickly. However, most meta-RL algorithms show poor generalization in multi-task scenarios due to the insufficient task information provided only by rewards. Language-conditioned meta-RL improves the generalization capability by matching language instructions with the agent's behaviors. While both behaviors and language instructions have symmetry, which can speed up human learning of new knowledge. Thus, combining symmetry and language instructions into meta-RL can help improve the algorithm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.10656","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/2209.10656/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":"2209.10656","created_at":"2026-07-05T06:27:42.353679+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.10656v2","created_at":"2026-07-05T06:27:42.353679+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.10656","created_at":"2026-07-05T06:27:42.353679+00:00"},{"alias_kind":"pith_short_12","alias_value":"TRPBHHDGILRS","created_at":"2026-07-05T06:27:42.353679+00:00"},{"alias_kind":"pith_short_16","alias_value":"TRPBHHDGILRSSZGP","created_at":"2026-07-05T06:27:42.353679+00:00"},{"alias_kind":"pith_short_8","alias_value":"TRPBHHDG","created_at":"2026-07-05T06:27:42.353679+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/TRPBHHDGILRSSZGP4K2JUF66G5","json":"https://pith.science/pith/TRPBHHDGILRSSZGP4K2JUF66G5.json","graph_json":"https://pith.science/api/pith-number/TRPBHHDGILRSSZGP4K2JUF66G5/graph.json","events_json":"https://pith.science/api/pith-number/TRPBHHDGILRSSZGP4K2JUF66G5/events.json","paper":"https://pith.science/paper/TRPBHHDG"},"agent_actions":{"view_html":"https://pith.science/pith/TRPBHHDGILRSSZGP4K2JUF66G5","download_json":"https://pith.science/pith/TRPBHHDGILRSSZGP4K2JUF66G5.json","view_paper":"https://pith.science/paper/TRPBHHDG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.10656&json=true","fetch_graph":"https://pith.science/api/pith-number/TRPBHHDGILRSSZGP4K2JUF66G5/graph.json","fetch_events":"https://pith.science/api/pith-number/TRPBHHDGILRSSZGP4K2JUF66G5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TRPBHHDGILRSSZGP4K2JUF66G5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TRPBHHDGILRSSZGP4K2JUF66G5/action/storage_attestation","attest_author":"https://pith.science/pith/TRPBHHDGILRSSZGP4K2JUF66G5/action/author_attestation","sign_citation":"https://pith.science/pith/TRPBHHDGILRSSZGP4K2JUF66G5/action/citation_signature","submit_replication":"https://pith.science/pith/TRPBHHDGILRSSZGP4K2JUF66G5/action/replication_record"}},"created_at":"2026-07-05T06:27:42.353679+00:00","updated_at":"2026-07-05T06:27:42.353679+00:00"}