Alec Koppel

We propose a new variant of PG methods for infinite-horizon problems that uses a random rollout horizon for the Monte-Carlo estimation of the policy gradient. Expand

An algorithm to learn optimal actions in convex distributed online problems is proposed to control the growth of global network regret. Expand

Reinforcement learning, mathematically described by Markov Decision Problems, may be approached either through dynamic programming or policy search. Expand

We consider stochastic optimization problems in multiagent settings, where a network of agents aims to learn parameters that are optimal in terms of a global convex objective, while giving preference to locally observed information. Expand

We consider discriminative dictionary learning in a distributed online setting, where a network of agents aims to learn, from sequential observations, statistical model parameters jointly with data-driven signal representations. Expand

We consider stochastic optimization problems in multi-agent settings where a network of agents aims to learn decision variables which are optimal in terms of a global objective, while giving preference to locally and sequentially observed information. Expand

We develop algorithms that find and track the optimal solution trajectory of time-varying convex optimization problems that consist of local and network-related objectives. Expand

We consider multiagent stochastic optimization problems over reproducing kernel Hilbert spaces. Expand

We propose algorithms with a discrete time-sampling scheme to find and track the solution trajectory based on prediction and correction steps, while sampling the problem data at a constant rate of 1/h. Expand

We consider stochastic nonparametric regression problems in a reproducing kernel Hilbert space (RKHS), an extension of expected risk minimization to nonlinear function estimation. Expand