no code implementations • 25 Mar 2024 • Titouan Renard, Andreas Schlaginhaufen, Tingting Ni, Maryam Kamgarpour
Furthermore, with $\mathcal{O}(1/\varepsilon^{4})$ samples we prove that the optimal policy corresponding to the recovered reward is $\varepsilon$-close to the expert policy in total variation distance.
no code implementations • 8 Jan 2024 • Kai Ren, Colin Chen, Hyeontae Sung, Heejin Ahn, Ian Mitchell, Maryam Kamgarpour
We present a chance-constrained model predictive control (MPC) framework under Gaussian mixture model (GMM) uncertainty.
no code implementations • 13 Dec 2023 • Reda Ouhamma, Maryam Kamgarpour
We consider decentralized learning for zero-sum games, where players only see their payoff information and are agnostic to actions and payoffs of the opponent.
no code implementations • 1 Dec 2023 • Tingting Ni, Maryam Kamgarpour
We consider discounted infinite horizon constrained Markov decision processes (CMDPs) where the goal is to find an optimal policy that maximizes the expected cumulative reward subject to expected cumulative constraints.
1 code implementation • 1 Jun 2023 • Andreas Schlaginhaufen, Maryam Kamgarpour
Two main challenges in Reinforcement Learning (RL) are designing appropriate reward functions and ensuring the safety of the learned policy.
2 code implementations • 21 Jul 2022 • Ilnura Usmanova, Yarden As, Maryam Kamgarpour, Andreas Krause
We introduce a general approach for seeking a stationary point in high dimensional non-linear stochastic optimization problems in which maintaining safety during learning is crucial.
no code implementations • 14 Mar 2022 • Pier Giuseppe Sessa, Maryam Kamgarpour, Andreas Krause
We consider model-based multi-agent reinforcement learning, where the environment transition model is unknown and can only be learned via expensive interactions with the environment.
1 code implementation • 13 Aug 2021 • Vasileios Lefkopoulos, Maryam Kamgarpour
We tackle the problem of trajectory planning in an environment comprised of a set of obstacles with uncertain time-varying locations.
no code implementations • 5 Aug 2021 • Heejin Ahn, Colin Chen, Ian M. Mitchell, Maryam Kamgarpour
We develop a computationally efficient, scenario-based approach that solves the motion planning problem with high confidence given a quantifiable number of samples from the multimodal distribution.
no code implementations • NeurIPS 2020 • Pier Giuseppe Sessa, Ilija Bogunovic, Andreas Krause, Maryam Kamgarpour
We formulate the novel class of contextual games, a type of repeated games driven by contextual information at each round.
1 code implementation • 2 Mar 2021 • Daniel Tihanyi, Yimeng Lu, Orcun Karaca, Maryam Kamgarpour
Computation of a multi-robot optimal control policy is challenging not only because of the complexity of incorporating dynamic uncertainties while planning, but also because of the exponential growth in problem size as a function of number of robots.
Robotics Optimization and Control
no code implementations • 17 Feb 2021 • Orcun Karaca, Stefanos Delikaraoglou, Maryam Kamgarpour
Considering the sequential clearing of energy and reserves in Europe, enabling inter-area reserve exchange requires optimally allocating inter-area transmission capacities between these two markets.
Optimization and Control Computer Science and Game Theory
no code implementations • 8 Sep 2020 • Tatiana Tatarenko, Maryam Kamgarpour
We address learning Nash equilibria in convex games under the payoff information setting.
Optimization and Control
1 code implementation • NeurIPS 2020 • Pier Giuseppe Sessa, Ilija Bogunovic, Maryam Kamgarpour, Andreas Krause
We consider a repeated sequential game between a learner, who plays first, and an opponent who responds to the chosen action.
no code implementations • L4DC 2020 • Ilnura Usmanova, Andreas Krause, Maryam Kamgarpour
For safety-critical black-box optimization tasks, observations of the constraints and the objective are often noisy and available only for the feasible points.
no code implementations • 5 Mar 2020 • Yimeng Lu, Maryam Kamgarpour
This paper considers safe robot mission planning in uncertain dynamical environments.
no code implementations • 28 Feb 2020 • Pier Giuseppe Sessa, Ilija Bogunovic, Maryam Kamgarpour, Andreas Krause
We consider robust optimization problems, where the goal is to optimize an unknown objective function against the worst-case realization of an uncertain parameter.
2 code implementations • 11 Dec 2019 • Baiwei Guo, Orcun Karaca, Tyler Summers, Maryam Kamgarpour
We then obtain performance guarantees for the forward and reverse greedy algorithms applied to the general class of matroid optimization problems by exploiting properties of the objective function such as the submodularity ratio and the curvature.
Optimization and Control
1 code implementation • NeurIPS 2019 • Pier Giuseppe Sessa, Ilija Bogunovic, Maryam Kamgarpour, Andreas Krause
We consider the problem of learning to play a repeated multi-agent game with an unknown reward function.
no code implementations • 13 Jun 2018 • Tatiana Tatarenko, Maryam Kamgarpour
The objective is to minimize the regret, that is, the difference between the sum of the costs she accumulates and that of a static optimal action had she known the sequence of cost functions a priori.