{"id":"https://openalex.org/G2290138457","display_name":"Collaborative: RI: Feature Discovery and Benchmarks for Exportable Reinforcement Learning","description":"Collaborative Proposal pair: 0713435 (Lead) & 0713148\r\n\"Collaborative: RI: Feature Discovery and Benchmarks for exportable Reinforcement Learning\"\r\nPI: Ronald Parr, Duke University\r\nPI: Michael L. Littman, Rutgers University\r\n\r\nABSTRACT\r\n\r\nThis project focuses on several aspects of automated feature discovery in the context of reinforcement learning. Badly chosen features cause reinforcement-learning algorithms to fail and, as such, only individuals skilled in feature construction can create successful reinforcement-learning systems for novel tasks. This issue underscores two shortcomings in existing research. First, most existing reinforcement-learning methods cannot generate or discover features automatically and robustly. Second, existing benchmark problems and paradigms for benchmarking do not distinguish adequately between clever algorithm design and clever feature engineering.\r\n\r\nThis project addresses these challenges in two-pronged approach. The first prong aims to advance a technical agenda leading to a new approach to feature discovery and model representation. The second prong is the development of a benchmark methodology and repository with a different focus and structure from existing endeavors. The goal for the benchmarking effort will be to produce a set of fair and reproducible experiments that will help elucidate the strengths and weaknesses of existing approaches, while simultaneously introducing challenges to motivate the development of new approaches.\r\n\r\n","funder_award_id":"0713435","funder":{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","doi":"https://doi.org/10.13039/100000001"},"funded_outputs":["https://openalex.org/W395196838","https://openalex.org/W1603806841","https://openalex.org/W2110486110","https://openalex.org/W2117481033","https://openalex.org/W2125710232","https://openalex.org/W2127186087","https://openalex.org/W2468008811"],"funded_outputs_count":7,"parent_awards":[],"sub_awards":[],"sub_awards_count":0,"amount":225000.0,"currency":"USD","amount_usd":225000.0,"amount_usd_basis":"usd_native","recipients":[],"recipient_countries":[],"recipient_regions":[],"research_scope":{"is_research":true,"basis":"funder_default","tier":1},"funding_type":"grant","funder_scheme":"Standard Grant","start_date":"2007-10-01","end_date":"2011-09-30","start_year":2007,"end_year":2011,"landing_page_url":"https://www.nsf.gov/awardsearch/showAward?AWD_ID=0713435","doi":null,"provenance":"nsf_award_search","lead_investigator":{"given_name":"Ronald","family_name":"Parr","orcid":null,"role_start":null,"affiliation":{"name":"Duke University","country":"","ids":null},"author":{"id":"https://openalex.org/A5109839104","display_name":"Ronald Parr","orcid":null},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}]},"co_lead_investigator":null,"investigators":null,"works_api_url":"https://api.openalex.org/works?filter=awards.id:G2290138457","primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/feature-discovery","display_name":"feature discovery","score":0.768},{"id":"https://openalex.org/keywords/automated-feature-engineering","display_name":"automated feature engineering","score":0.694},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.551},{"id":"https://openalex.org/keywords/model-representation","display_name":"model representation","score":0.704},{"id":"https://openalex.org/keywords/reproducibility","display_name":"reproducibility","score":0.734},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.349}],"sustainable_development_goals":[],"institution_awarded":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"updated_date":"2026-11-13T03:01:57.000Z","created_date":"2026-07-13T04:41:43.000Z"}
