170 citations · 506 across the 51 of their papers we have counts for
7 papers · 1 filter
On the Sample Complexity of Actor-Critic Method for Reinforcement Learning with Function Approximation
Harshat Kumar, Alec Koppel, Alejandro Ribeiro
Reinforcement learning, mathematically described by Markov Decision Problems, may be approached either through dynamic programming or policy search. Actor-critic algorithms combine…
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…
Optimally Compressed Nonparametric Online Learning
Alec Koppel, Amrit Singh Bedi, Ketan Rajawat +1
Batch training of machine learning models based on neural networks is now well established, whereas to date streaming methods are largely based on linear models. To go beyond linea…
Nearly Consistent Finite Particle Estimates in Streaming Importance Sampling
Alec Koppel, Amrit Singh Bedi, Brian M. Sadler +1
In Bayesian inference, we seek to compute information about random variables such as moments or quantiles on the basis of {available data} and prior information. When the distribut…
Adaptive Kernel Learning in Heterogeneous Networks
Hrusikesha Pradhan, Amrit Singh Bedi, Alec Koppel +1
We consider learning in decentralized heterogeneous networks: agents seek to minimize a convex functional that aggregates data across the network, while only having access to their…
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…