Evolutionary robotics and game-AI researcher at Connecticut College with a sharp recent output surge
2
papers here
2
reviewed by Evolve
2
first-author
0
corresponding
—
works · OpenAlex
12
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-15) and cover the author's entire public record, not just the papers listed here. Reproducibility signal comes from Evolve's own reviews.
Research profile
Output—
Unscored: the snapshot lacks sufficient verified publication records for this axis, though it lists an h-index of 12 and an i10-index of 21. Output would measure total scholarly production and its consistency over time.
Impact—
Unscored: citation coverage in the snapshot is insufficient for a verified rating. Impact would measure citation-based influence — citations per work and field-weighted reach — once fuller bibliographic linkage is available.
Focus0/100
The focus score of 0 reflects an evenly split record: the field distribution assigns 0.5 to evolutionary computation (game AI / multi-agent systems) and 0.5 to evolutionary robotics. Five topic clusters — led by Evolutionary Algorithms and Applications with 88 works — confirm breadth spanning locomotion, swarm systems, reinforcement learning, and games rather than concentration in one lane.
Collaboration22/100
Collaboration scores 22, consistent with a small-team style: only 2 distinct coauthors appear in the recent window, with Jim O'Connor and John Asaro as the recurring partners. Both 2026 catalog papers are first-authored efforts without a corresponding-author flag, so co-authorship breadth — not productivity — is the limiting factor.
Activity91/100
Activity is the strongest dimension at 91. The snapshot records 22 works in the last three years, and yearly counts climb from 2 (2023) and 2 (2024) to 7 (2025) and 13 (2026) — the busiest stretch since the 2005–2006 peak of 8 and 11 publications.
Reproducibility38/100
Reproducibility averages 38 across 2 Evolve-reviewed papers. Both are genetic-algorithm studies with simulators in place, but reviews note absent statistical tests, figure-only results, and no centralized-GA or external baselines; readiness is medium for the hexapod-gait paper and low for The Core niching agents.
Research summary
Gary B. Parker, listed at Connecticut College (US), is an evolutionary-computation researcher whose record — name-resolved from OpenAlex bibliographic data — splits evenly between evolutionary robotics and evolutionary computation for game AI and multi-agent systems (field distribution 0.5/0.5). Topic concentrations lead with Evolutionary Algorithms and Applications (88 works), followed by Modular Robots and Swarm Intelligence (51), Robotic Locomotion and Control (41), Reinforcement Learning in Robotics (33), and Artificial Intelligence in Games (30). The snapshot lists an h-index of 12 and an i10-index of 21, but citation coverage is insufficient for Evolve to score the output and impact axes. Activity is the strongest dimension (91): 22 works in the last three years, climbing from 2 indexed publications in 2023 to 7 in 2025 and 13 in 2026 — the busiest stretch since the 2005–2006 peak of 8 and 11. Collaboration is thin (22), with 2 distinct recent coauthors; Jim O'Connor and John Asaro recur. Two 2026 first-authored arXiv preprints are in the Evolve catalog: decentralized evolution of hexapod gaits with independent leg controllers (medium reproducibility readiness) and quadrant-niched agents for The Core in Xpilot (low). Evolve reviews flag missing statistical tests and absent centralized-GA or external baselines; mean reproducibility across 2 reviewed papers is 38.
Collaboration pattern
The record shows a small collaboration footprint: only 2 distinct coauthors in the recent window and a collaboration dimension score of 22. Jim O'Connor and John Asaro are the recurring partners, and both 2026 catalog papers are first-authored with no corresponding-author flag. The pattern points to lab-internal, simulator-based projects where Parker leads the evolutionary-method design while coauthors contribute implementation and testing, rather than large multi-institution teams.
Research keywords
Highlights
Decentralized hexapod gait evolution with independent leg controllers
Quadrant-niched agents for The Core in Xpilot
Late-career output surge
After sparse years (2 indexed publications each in 2023 and 2024), output rebounded to 7 works in 2025 and 13 in 2026, with 22 works in the trailing three years — the strongest activity signal in the profile (score 91).
Timeline
- 1993Earliest indexed publications appear (2 works), opening the OpenAlex-indexed record that later concentrates on evolutionary algorithms.
- 2006Peak indexed output: 11 publications, on the heels of 8 in 2005 — the most productive stretch of the earlier career phase.
- 2011Sustained mid-period output: 7 publications, matching 2010 and followed by 6 in 2012.
- 2025Output rebounds to 7 publications after sparse years (2 works each in 2023 and 2024), bringing the trailing three-year total to 22.
- 2026Two first-authored arXiv preprints enter the Evolve catalog — decentralized hexapod-gait evolution and niching agents in The Core — amid 13 indexed works this year.
Papers in the Evolve catalog
Frequent co-authors
About this profile
This profile is AI-structured by Evolve.Pub from public bibliographic data (OpenAlex) and Evolve's own paper reviews. It is not written or endorsed by the researcher unless the profile is claimed. Radar dimensions are computed from real bibliometrics with fixed formulas — raw figures are shown alongside; missing dimensions mean insufficient data, never zero. Errors? Claim the profile to correct or hide it.
- Bibliometrics come from an OpenAlex snapshot (identity: openalex); citation coverage is insufficient, so the output and impact axes are unscored.
- The name 'Gary B. Parker' may not be unique; the profile is resolved from public bibliographic data with ORCID 0009-0001-3870-1190 listed, and no biography, awards, or career facts beyond this snapshot are asserted.
- Reproducibility (mean 38) rests on only 2 Evolve-reviewed papers, both 2026 arXiv preprints, and may not represent the full record.
- countsByYear omits several calendar years (e.g., 2014, 2017, 2018, 2020, 2022); zeros there reflect absent indexed records, not confirmed inactivity.