37 citations · 56 across the 13 of their papers we have counts for
5 papers · 1 filter
Convergence Rates of Average-Reward Multi-agent Reinforcement Learning via Randomized Linear Programming
Alec Koppel, Amrit Singh Bedi, Bhargav Ganguly +1
In tabular multi-agent reinforcement learning with average-cost criterion, a team of agents sequentially interacts with the environment and observes local incentives. We focus on t…
Nonstationary Nonparametric Online Learning: Balancing Dynamic Regret and Model Parsimony
Amrit Singh Bedi, Alec Koppel, Ketan Rajawat +1
An open challenge in supervised learning is \emph{conceptual drift}: a data point begins as classified according to one label, but over time the notion of that label changes. Beyon…
Global Convergence of Policy Gradient Methods to (Almost) Locally Optimal Policies
Kaiqing Zhang, Alec Koppel, Hao Zhu +1
Policy gradient (PG) methods are a widely used reinforcement learning methodology in many applications such as video games, autonomous driving, and robotics. In spite of its empiri…
Nonparametric Compositional Stochastic Optimization for Risk-Sensitive Kernel Learning
Amrit Singh Bedi, Alec Koppel, Ketan Rajawat +1
In this work, we address optimization problems where the objective function is a nonlinear function of an expected value, i.e., compositional stochastic {strongly convex programs}.…
Asynchronous Decentralized Stochastic Optimization in Heterogeneous Networks
Amrit Singh Bedi, Alec Koppel, Ketan Rajawat
We consider expected risk minimization in multi-agent systems comprised of distinct subsets of agents operating without a common time-scale. Each individual in the network is charg…