{"database": "team-science", "table": "paper", "rows": [["doi:10.1007/978-3-642-27645-3_2", "10.1007/978-3-642-27645-3_2", "W192920577", null, null, null, null, null, "Batch Reinforcement Learning", 2012, "Adaptation, learning, and optimization", "Computer Science", "https://openalex.org/fields/17", "https://doi.org/10.1007/978-3-642-27645-3_2", "2026-09-02T02:37:09Z", "openalex"]], "columns": ["lom_id", "doi", "openalex", "s2_paper_id", "arxiv", "pmid", "pmcid", "acl", "title", "year", "venue", "primary_field", "primary_field_id", "oa_url", "ingested_ts", "source"], "primary_keys": ["lom_id"], "primary_key_values": ["doi:10.1007/978-3-642-27645-3_2"], "units": {}, "query_ms": 0.5849208682775497, "source": "TeamScience Space repository", "source_url": "https://commons.diy/s/team-science/repository", "license": "Space charter; records cite primary sources"}