Joe Eappen
Scholar

Joe Eappen

Google Scholar ID: 98R6dEQAAAAJ
PhD Candidate, Purdue University
Multi Agent SystemsSafe Reinforcement Learning
Citations & Impact
All-time
Citations
61
 
H-index
4
 
i10-index
2
 
Publications
11
 
Co-authors
5
list available
Resume (English only)
Academic Achievements
  • Paper 'FLoRA: A Framework for Learning Scoring Rules in Autonomous Driving Planning Systems' accepted to IEEE RA-L (2025)
  • Paper 'Scaling Safe Multi-Agent Control for Signal Temporal Logic Specifications' accepted to CoRL 2024
  • Paper 'Information-Directed Pessimism for Offline Reinforcement Learning' accepted to ICML 2024
  • Paper 'Co-learning Planning and Control Policies Constrained by Differentiable Logic Specifications' accepted to ICRA 2024
  • Paper 'Online MCMC Thinning with Kernelized Stein Discrepancy' published in SIAM Journal on Mathematics of Data Science (SIMODS)
  • Two papers accepted to ECML PKDD 2022: one on Temporal Logic controllers for Multi-agent RL systems, and another on Adversarial Attacks to RL controllers
  • Paper 'Model-free Neural Lyapunov Control for Safe Robot Navigation' accepted to IROS 2022
  • US Patent Application: 'System and method for providing information-directed pessimism for offline reinforcement learning' (No. 18/379,406, filed Oct 2023, published as US20250124334A1)
  • Served as reviewer for top-tier conferences including ICML, NeurIPS, ICLR, AAAI, IROS, ICRA, and CoRL; recognized as Top Reviewer for ICML and NeurIPS in 2025