Search Results for author:
Found 24 papers, 5 papers with code
Anchor-Changing Regularized Natural Policy Gradient for Multi-Objective Reinforcement Learning
We study policy optimization for Markov decision processes (MDPs) with multiple reward value functions, which are to be jointly optimized according to given criteria such as proportional fairness (smooth concave scalarization), hard constraints (constrained MDP), and max-min trade-off.
Learning from Few Samples: Transformation-Invariant SVMs with Composition and Locality at Multiple Scales
Motivated by the problem of learning with small sample sizes, this paper shows how to incorporate into support-vector machines (SVMs) those properties that have made convolutional neural networks (CNNs) successful.
Terra: Blockage Resilience in Outdoor mmWave Networks
This allows the mobile to maintain time-synchronization with the base station, allowing it to revert to the LoS path when the temporary blockage disappears.
Natural Actor-Critic for Robust Reinforcement Learning with Function Approximation
We study robust reinforcement learning (RL) with the goal of determining a well-performing policy that is robust against model mismatch between the training simulator and the testing environment.
Stay With Me: Lifetime Maximization Through Heteroscedastic Linear Bandits With Reneging
Sequential decision making for lifetime maximization is a critical problem in many real-world applications, such as medical treatment and portfolio selection.
Throughput Optimal Decentralized Scheduling of Multi-Hop Networks with End-to-End Deadline Constraints: II Wireless Networks with Interference
The key difference arises due to the fact that in our set-up the packets loose their utility once their "age" has crossed their deadline, thus making the task of optimizing timely throughput much more challenging than that of ensuring network stability.
Belief Space Planning Simplified: Trajectory-Optimized LQG (T-LQG) (Extended Report)
Planning under motion and observation uncertainties requires solution of a stochastic control problem in the space of feedback policies.
Robotics Optimization and Control
Exploration Through Reward Biasing: Reward-Biased Maximum Likelihood Estimation for Stochastic Multi-Armed Bandits
To choose the bias-growth rate $\alpha(t)$ in RBMLE, we reveal the nontrivial interplay between $\alpha(t)$ and the regret bound that generally applies in both the Exponential Family as well as the sub-Gaussian/Exponential family bandits.
Learning in Networked Control Systems
We design adaptive controller (learning rule) for a networked control system (NCS) in which data packets containing control information are transmitted across a lossy wireless channel.
Reward-Biased Maximum Likelihood Estimation for Linear Stochastic Bandits
Modifying the reward-biased maximum likelihood method originally proposed in the adaptive control literature, we propose novel learning algorithms to handle the explore-exploit trade-off in linear bandits problems as well as generalized linear bandits problems.
Reward Biased Maximum Likelihood Estimation for Reinforcement Learning
The Reward-Biased Maximum Likelihood Estimate (RBMLE) for adaptive control of Markov chains was proposed to overcome the central obstacle of what is variously called the fundamental "closed-identifiability problem" of adaptive control, the "dual control problem", or, contemporaneously, the "exploration vs. exploitation problem".
An Efficient Network Solver for Dynamic Simulation of Power Systems Based on Hierarchical Inverse Computation and Modification
In power system dynamic simulation, up to 90% of the computational time is devoted to solve the network equations, i. e., a set of linear equations.
Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPs
We show that when a strictly safe policy is known, then one can confine the system to zero constraint violation with arbitrarily high probability while keeping the reward regret of order $\tilde{\mathcal{O}}(\sqrt{K})$.
Silent Tracker: In-band Beam Management for Soft Handover for mm-Wave Networks
In mm-wave networks, cell sizes are small due to high path and penetration losses.
BeamSurfer: Minimalist Beam Management of Mobile mm-Wave Devices
Management of narrow directional beams is critical for mm-wave communication systems.
Policy Optimization for Constrained MDPs with Provable Fast Global Convergence
We propose a new algorithm called policy mirror descent-primal dual (PMD-PD) algorithm that can provably achieve a faster $\mathcal{O}(\log(T)/T)$ convergence rate for both the optimality gap and the constraint violation.
Augmented RBMLE-UCB Approach for Adaptive Control of Linear Quadratic Systems
We consider the problem of controlling an unknown stochastic linear system with quadratic costs - called the adaptive LQ control problem.
On an Information and Control Architecture for Future Electric Energy Systems
This paper presents considerations towards an information and control architecture for future electric energy systems driven by massive changes resulting from the societal goals of decarbonization and electrification.
Energy System Digitization in the Era of AI: A Three-Layered Approach towards Carbon Neutrality
The transition towards carbon-neutral electricity is one of the biggest game changers in addressing climate change since it addresses the dual challenges of removing carbon emissions from the two largest sectors of emitters: electricity and transportation.
TERRA: Beam Management for Outdoor mm-Wave Networks
To avoid outage in transient pedestrian blockage of the LoS path, the mobile uses reflected or NLoS path available in indoor environments.
Bounded (O(1)) Regret Recommendation Learning via Synthetic Controls Oracle
In online exploration systems where users with fixed preferences repeatedly arrive, it has recently been shown that O(1), i. e., bounded regret, can be achieved when the system is modeled as a linear contextual bandit.
Finite Time Regret Bounds for Minimum Variance Control of Autoregressive Systems with Exogenous Inputs
Minimum variance controllers have been employed in a wide-range of industrial applications.
Value-Biased Maximum Likelihood Estimation for Model-based Reinforcement Learning in Discounted Linear MDPs
We consider the infinite-horizon linear Markov Decision Processes (MDPs), where the transition probabilities of the dynamic model can be linearly parameterized with the help of a predefined low-dimensional feature mapping.
Provable Policy Gradient Methods for Average-Reward Markov Potential Games
We prove that both algorithms based on independent policy gradient and independent natural policy gradient converge globally to a Nash equilibrium for the average reward criterion.
