Scholar
Aditya Kapoor
Google Scholar ID: UPH3tawAAAAJ
ELLIS PhD @ University of Manchester
Citations & Impact
Citations
59
H-index
4
i10-index
2
Publications
19
Co-authors
16
list available
Publications
Resume (English only)
Academic Achievements
- Publications:
- - 'Low-Rank Agent-Specific Adaptation (LoRASA) for Multi-Agent Policy Learning', DAI 2025
- - 'Assigning Credit with Partial Reward Decoupling in Multi-Agent Proximal Policy Optimization', RLC 2024
- - 'Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environments', NeurIPS 2024
- - 'MAP-THOR: Benchmarking Long-Horizon Multi-Agent Planning Frameworks in Partially Observable Environments', ICML 2024
- - 'Agent-Temporal Credit Assignment for Optimal Policy Preservation in Sparse Multi-Agent Reinforcement Learning', RLC 2024
- - 'SocNavGym: A Reinforcement Learning Gym for Social Navigation', IEEE RO-MAN, 2023
- - 'Concept-based Anomaly Detection in Retail Stores for Automatic Correction using Mobile Robots', IEEE SMCS, 2023
Research Experience
- Position: ELLIS PhD student; Work Experience: Prior to the PhD, worked as a predoctoral researcher at Tata Consultancy Services Research & Innovation in Mumbai, collaborating with Dr. Mayank Baranwal and Dr. Harshad Khadilkar. Also briefly worked with Dr. Vighnesh Vatsal and Dr. Jay Gubbi in TCS Bangalore.
Education
- Degree: PhD; Schools: University of Manchester and TU Darmstadt; Advisors: Omar Rivasplata, Samuel Kaski, Jan Peters; Time: Last updated in October 2025; Bachelor: Bachelor of Engineering in Computer Science, BITS Pilani, Goa.
Background
- Research Interests: Multi-agent systems, reinforcement learning, and foundation models, with a focus on building agents capable of effective communication and collaboration. Broadly interested in all facets of multi-agent systems, from foundational theory to practical application. Draws insights and tools from an interdisciplinary array of fields including information theory, cognitive science, and robotics.
Miscellany
- Contact: aditya [dot] kapoor [at] postgrad [dot] manchester [dot] ac [dot] uk
