← Authors

Alec Koppel

26 papers · 2019–2025 · 7 conferences · across top CS/AI conferences

Achievements

πŸƒ Academic Marathon (6) 🌈 Renaissance Researcher (5) πŸ—ΊοΈ Taxonomy Completionist (30) 🌍 Conference Polyglot (7) 🐝 Cross-Pollinator (12) 🧭 Keyword Pioneer πŸŒ‰ Interdisciplinary Bridge 🐣 Hot Topic Early Bird πŸ† Keyword Champion (2) πŸ† Grand Slam πŸ—ƒοΈ Keyword Collector (93) πŸš€ Conference Pioneer πŸ’Ž Century Club (26) ⚑ Prolific Year (5)

Conferences

ICML (7) AAAI (4) AISTATS (4) ICLR (4) JMLR (3) L4DC (2) NIPS (2)

Top co-authors

Mengdi Wang (8) Dinesh Manocha (7) Sumitra Ganesh (7) Amrit Singh Bedi (7) Souradip Chakraborty (6) Furong Huang (6) Sujay Bhatt (6) Amrit Bedi (5) Junyu Zhang (3) Vaneet Aggarwal (3)

Keywords

multi-agent reinforcement learning (3) policy gradient (3) sample complexity (3) reinforcement learning (3) model-based reinforcement learning (2) policy optimization (2) stochastic gradient descent (2) superlinear convergence (2) mean-field game (2) primal-dual optimization (2) hessian approximation (2) general utility (2) quasi-newton method (2) utility optimization (1) numerical optimization (1) distributed learning (1) online learning (1) nonparametric regression (1) zero constraint violation (1) policy search (1)

Papers

Decentralized Convergence to Equilibrium Prices in Trading Networks AAAI 2025
GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-Time Alignment ICLR 2025
Collab: Controlled Decoding using Mixture of Agents for LLM Alignment ICLR 2025
Approximate Equivariance in Reinforcement Learning AISTATS 2025
Learning in Herding Mean Field Games: Single-Loop Algorithm with Finite-Time Convergence Analysis AISTATS 2025
Robust cooperative multi-agent reinforcement learning: A mean-field type game perspective L4DC 2024
Sharpened Lazy Incremental Quasi-Newton Method AISTATS 2024
Efficient Inverse Multiagent Learning ICLR 2024
PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback ICLR 2024
MaxMin-RLHF: Alignment with Diverse Human Preferences ICML 2024
Information-Directed Pessimism for Offline Reinforcement Learning ICML 2024
Towards Global Optimality for Practical Average Reward Reinforcement Learning without Mixing Time Oracles ICML 2024
On the Sample Complexity and Metastability of Heavy-tailed Policy Search in Continuous Control JMLR 2024
Scalable Primal-Dual Actor-Critic Method for Safe Multi-Agent RL with General Utilities NIPS 2023
STEERING : Stein Information Directed Exploration for Model-Based Reinforcement Learning ICML 2023
Beyond Exponentially Fast Mixing in Average-Reward Reinforcement Learning via Multi-Level Monte Carlo Actor-Critic ICML 2023
Oracle-free Reinforcement Learning in Mean-Field Games along a Single Sample Path AISTATS 2023
Posterior Coreset Construction with Kernelized Stein Discrepancy for Model-Based Reinforcement Learning AAAI 2023
On the Hidden Biases of Policy Mirror Ascent in Continuous Action Spaces ICML 2022
Sharpened Quasi-Newton Methods: Faster Superlinear Rate and Larger Local Convergence Neighborhood ICML 2022
Multi-Agent Reinforcement Learning with General Utilities via Decentralized Shadow Reward Actor-Critic AAAI 2022
Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Primal-Dual Approach AAAI 2022
Efficient Large-Scale Gaussian Process Bandits by Believing only Informative Actions L4DC 2020
Variational Policy Gradient Method for Reinforcement Learning with General Utilities NIPS 2020
A Class of Parallel Doubly Stochastic Algorithms for Large-Scale Learning JMLR 2020
Parsimonious Online Learning with Kernels via Sparse Projections in Function Space JMLR 2019