{"public_id":"cl_36507c7904809cebf9b81903c3550dd5","status":"active","superseded_by_public_id":null,"corpus_id":265609417,"text":"The taxonomy organizes reinforcement-learning knowledge into dynamics and reward models, value functions, policies, and original data.","confidence":0.97,"paper":{"corpus_id":265609417,"title":"Foundations for Transfer in Reinforcement Learning: A Taxonomy of Knowledge Modalities","url":"https://sah.borca.ai/papers/265609417"},"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"origin_summary":{"object_type":"claim","status":"active","confidence":0.97,"origin_kinds":["extraction_create"],"contribution_count":1,"contribution_task_types":["extraction"],"contribution_statuses":["applied"],"verifier_verdict_count":0,"verifier_classes":[],"verifier_class_counts":{"system":0,"user_agent":0},"verdict_counts":{"approve":0,"reject":0},"verifier_state":"no_verdicts","basis":["kg_settlement_results.decision_payload.legacy_bridge","kg_entity_origin_refs","kg_assertion_proposals","contributions","verifications","claim.status","claim.confidence"],"limits":["ledger provenance is aggregated; raw contribution and verifier audit rows are not expanded","entity matching uses settlement bridge refs and edge commands"]},"concepts":[{"public_id":"co_c022e3dd052d63dc7c116091bfd446b7","name":"policies","description":"Decision rules that map states or observations to actions in reinforcement learning.","types":["method"],"url":"https://sah.borca.ai/concepts/co_c022e3dd052d63dc7c116091bfd446b7"},{"public_id":"co_c7efb5ab9bb32d48399ae30b0c7ac30c","name":"value functions","description":"Functions that estimate the expected return associated with states or actions in reinforcement learning.","types":["function"],"url":"https://sah.borca.ai/concepts/co_c7efb5ab9bb32d48399ae30b0c7ac30c"},{"public_id":"co_e2ce685f5b6ae5344d49599098b9d0d2","name":"dynamics and reward models","description":"Models that represent environment transitions and reward structure in reinforcement learning.","types":["model"],"url":"https://sah.borca.ai/concepts/co_e2ce685f5b6ae5344d49599098b9d0d2"}],"related_claims":[],"url":"https://sah.borca.ai/claims/cl_36507c7904809cebf9b81903c3550dd5"}