arXiv research

Paper tackles efficient navigation in constrained environments using supervised and reinforcement learning.

FAVANO improves federated learning for resource-constrained environments.

Active learning agents typically employ a query selection algorithm which solely considers the agent's learning objectives. However, this may be insufficient in more realistic human domains. This work uses imitation learning to enable an agent in a constrained environment to concurrently reason about both its internal …

New algorithm ensures consistent results in constrained MAB problems.

Offline RL tackles resource-constrained online deployment with improved policy transfer.

New algorithm for reinforcement learning in uncertain environments with unknown thresholds.

Improved distributed learning with reduced communication costs.

Algorithm tackles constrained reinforcement learning with concave-convex and knapsack constraints.

As integrated circuits have become progressively more complex, constrained random stimulus has become ubiquitous as a means of stimulating a designs functionality and ensuring it fully meets expectations. In theory, random stimulus allows all possible combinations to be exercised given enough time, but in practice with…

Meta-learning improves drone trajectory design for dynamic wireless networks.

VaR-CPO optimizes VaR-constrained RL problems with conservative policy updates.

This paper considers online convex optimization (OCO) with stochastic constraints, which generalizes Zinkevich's OCO over a known simple fixed set by introducing multiple stochastic functional constraints that are i.i.d. generated at each round and are disclosed to the decision maker only after the decision is made. Th…

Paper uses RL to solve constrained combinatorial optimization problems.

In order to satisfy safety conditions, an agent may be constrained from acting freely. A safe controller can be designed a priori if an environment is well understood, but not when learning is employed. In particular, reinforcement learned (RL) controllers require exploration, which can be hazardous in safety critical …

This paper introduces a new approach to active inference using constrained Bethe Free Energy.

MixDiff detects OOD samples in constrained access environments by comparing perturbed samples.

KL-constrained API shows optimization issues and improved with regularization.

FOCOPS optimizes agent's behavior while adhering to constraints.

New algorithms control loss and constraints in uncertain, changing environments.

Recurrent Neural Networks (RNN) can be difficult to deploy on resource constrained devices due to their size. As a result, there is a need for compression techniques that can significantly compress RNNs without negatively impacting task accuracy. This paper introduces a method to compress RNNs for resource constrained …

We present a novel method for learning a set of disentangled reward functions that sum to the original environment reward and are constrained to be independently obtainable. We define independent obtainability in terms of value functions with respect to obtaining one learned reward while pursuing another learned reward…

Opportunistic spectrum access is one of the emerging techniques for maximizing throughput in congested bands and is enabled by predicting idle slots in spectrum. We propose a kernel-based reinforcement learning approach coupled with a novel budget-constrained sparsification technique that efficiently captures the envir…

Adversarial attacks have exposed a significant security vulnerability in state-of-the-art machine learning models. Among these models include deep reinforcement learning agents. The existing methods for attacking reinforcement learning agents assume the adversary either has access to the target agent's learned paramete…

Constrained Markov Decision Processes are a class of stochastic decision problems in which the decision maker must select a policy that satisfies auxiliary cost constraints. This paper extends upper confidence reinforcement learning for settings in which the reward function and the constraints, described by cost functi…

CoCoRL learns safe constraints from demonstrations with unknown rewards.

Unified framework for constrained online decision-making.

Deep Neural Networks (DNNs) are increasingly deployed in highly energy-constrained environments such as autonomous drones and wearable devices while at the same time must operate in real-time. Therefore, reducing the energy consumption has become a major design consideration in DNN training. This paper proposes the fir…

Bayesian method optimizes uncertain constraints in black-box function optimization.

T-Basis represents neural network tensors with fewer parameters.

In recent years, a myriad of advanced results have been reported in the community of imitation learning, ranging from parametric to non-parametric, probabilistic to non-probabilistic and Bayesian to frequentist approaches. Meanwhile, ample applications (e.g., grasping tasks and human-robot collaborations) further show …

Investigates safe decision-making in interactive environments.

learn2mix trains neural nets faster by adjusting class proportions dynamically.

Paper robustifies reinforcement learning with risk-averse methods.

A novel method for efficient CDRL over wireless networks.

Interactive Fiction games are text-based simulations in which an agent interacts with the world purely through natural language. They are ideal environments for studying how to extend reinforcement learning agents to meet the challenges of natural language understanding, partial observability, and action generation in …

CriticSMC improves planning efficiency in constrained environments.

Decentralized learning for matching markets with time-varying preferences.

We propose a novel training algorithm for reinforcement learning which combines the strength of deep Q-learning with a constrained optimization approach to tighten optimality and encourage faster reward propagation. Our novel technique makes deep reinforcement learning more practical by drastically reducing the trainin…

New RL approach tackles constrained Markov decision processes.

Widely-used deep reinforcement learning algorithms have been shown to fail in the batch setting--learning from a fixed data set without interaction with the environment. Following this result, there have been several papers showing reasonable performances under a variety of environments and batch settings. In this pape…

We observe that several existing policy gradient methods (such as vanilla policy gradient, PPO, A2C) may suffer from overly large gradients when the current policy is close to deterministic (even in some very simple environments), leading to an unstable training process. To address this issue, we propose a new method, …

This paper studies a class of non$-$Markovian singular stochastic control problems, for which we provide a novel probabilistic representation. The solution of such control problem is proved to identify with the solution of a $Z-$constrained BSDE, with dynamics associated to a non singular underlying forward process. Du…

Study proposes adaptive RL for dynamic portfolio optimization.

Paper proposes DP-PASGD for efficient, private IoT learning.

Controller-Augmented Hidden Markov Models (CHMMs) are a framework for constrained sequential inference.

A method to learn robust policies for environments with model mismatches.

Smart and agile drones are fast becoming ubiquitous at the edge of the cloud. The usage of these drones are constrained by their limited power and compute capability. In this paper, we present a Transfer Learning (TL) based approach to reduce on-board computation required to train a deep neural network for autonomous n…

RIA method improves OoD generalization for covariate shift.