New RL algorithm reduces policy switching cost to loglog(T) with similar regret.
problem Low policy switching cost in real-life RL applications.
method Stage-wise exploration and adaptive policy elimination.
result Regret of with switching cost.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,742 papers · 148 categories
Trend · papers per month
48 results for “policy switching cost”
Study tackles balancing policy switching costs in offline RL.
problem Balancing the cost of policy switching in offline RL.
method Optimal transport ideas and Net Actor-Critic algorithm.
result Demonstrated efficiency on multiple RL benchmarks.
Regret-Optimal Q-Learning with Low Cost for Single-Agent and Federated Reinforcement Learningstat.ML
New RL algorithms reduce costs for single-agent and federated learning.
problem Minimizing costs in RL and federated RL settings.
method Q-EarlySettled-LowCost and FedQ-EarlySettled-LowCost algorithms.
result First algorithms to achieve low burn-in and logarithmic switching costs.
New algorithm reduces switching costs in RL beyond linear MDPs.
problem Costly policy switching in reinforcement learning.
method ELEANOR-LowSwitching algorithm for linear Bellman-complete MDPs.
result Achieves near-optimal regret with logarithmic switching cost.
New algorithm reduces RL complexity with low switching costs.
problem Exploration-exploitation dilemma in RL with complex models.
method Monotonic Q-Learning with Upper Confidence Bound (MQL-UCB) for RL with general function approximation.
result Achieves minimax optimal regret of and near-optimal policy switching cost.
New algorithm reduces decision switching in dynamic environments.
problem Online learning with memory and non-stationary environments.
method Dynamic policy regret, novel ensemble approach, meta-base decomposition.
result Proves optimal dynamic policy regret for memory length, non-stationarity, and time horizon.
Paper presents an efficient algorithm for linear MDP with low switching cost.
problem Large state space reinforcement learning problems with low switching cost.
method First algorithm for linear MDP with low switching cost, achieving near-optimal regret and switching cost.
result Regret bound of $\widetilde{O}\left(\sqrt{d^3H^4K}
ight)$ and near-optimal switching cost of $O\left(d H\log K
ight)$.
We take initial steps in studying PAC-MDP algorithms with limited adaptivity, that is, algorithms that change its exploration policy as infrequently as possible during regret minimization. This is motivated by the difficulty of running fully adaptive algorithms in real-world applications (such as medical domains), and …
This paper tackles near-optimal adversarial RL with switching costs, providing algorithms and matching lower bounds.
problem Adversarial RL with switching costs, where loss distribution can be non-stationary or adversarial.
method Developed novel switching-reduced algorithms with matching lower bounds for known and unknown transition functions.
result Achieved near-optimal performance in adversarial RL with switching costs, matching theoretical lower bounds.
We study the power of different types of adaptive (nonoblivious) adversaries in the setting of prediction with expert advice, under both full-information and bandit feedback. We measure the player's performance using a new notion of regret, also known as policy regret, which better captures the adversary's adaptiveness…
Breaks down complex nonlinear dynamics into simpler components.
problem Control of nonlinear dynamical systems remains challenging.
method Inspired by hybrid switching systems, decomposes dynamics into simpler stochastic switching linear dynamical systems.
result Extracts hierarchies of Markovian and auto-regressive locally linear controllers from nonlinear experts.
Paper tackles online optimization with memory and competitive control.
problem Minimizing hitting and switching costs in online optimization problems.
method Optimistic Regularized Online Balanced Descent algorithm.
result Achieves a constant, dimension-free competitive ratio.
We study the adversarial multi-armed bandit problem where partial observations are available and where, in addition to the loss incurred for each action, a \emph{switching cost} is incurred for shifting to a new action. All previously known results incur a factor proportional to the independence number of the feedback …
This paper improves Q-learning bounds using reference-advantage decomposition.
problem Improving Q-learning bounds in MDPs with positive suboptimality gaps.
method Develops a novel error decomposition framework to prove gap-dependent regret bounds.
result Establishes logarithmic gap-dependent regret bounds for Q-learning.
New algorithm reduces switching costs in multinomial logit bandit problems.
problem Minimizing switching costs in multinomial logit bandit problems.
method Proposed AT-DUCB and FH-DUCB algorithms with low assortment switching costs.
result AT-DUCB and FH-DUCB algorithms achieve almost optimal minimax regret with low switching costs.
New algorithm learns optimal policies with minimal memory and time.
problem Learning optimal policies in discounted MDPs with short burn-in time.
method Variance reduction and adaptive policy switching.
result First regret-optimal model-free algorithm with low burn-in time.
The paper explores dynamic regret with switching cost in online decision making.
problem The relation between dynamic regret and switching cost in online decision making.
method Investigates two classic online settings: Online Algorithms (OA) and Online Convex Optimization (OCO). Provides a new theoretical analysis framework.
result The switching cost impacts dynamic regret differently in OA and has no impact in OCO.
The problem of optimal switching between nonlinear autonomous subsystems is investigated in this study where the objective is not only bringing the states to close to the desired point, but also adjusting the switching pattern, in the sense of penalizing switching occurrences and assigning different preferences to util…
A new policy switching technique improves offline RL performance.
problem Challenges in adapting off-policy algorithms to different datasets and tasks.
method Combines off-policy RL and BC, using epistemic uncertainty for policy switching.
result Outperforms individual algorithms and state-of-the-art methods on benchmarks.
LaMBO optimizes modular systems with switching costs, achieving better results than existing methods.
problem Optimizing systems with costly variable updates in a sequence of modules.
method Lazy Modular Bayesian Optimization (LaMBO) that minimizes switching costs.
result LaMBO achieves vanishing regret and improves over existing cost-aware Bayesian optimization algorithms.
Algorithm selects best model based on state, reducing costs.
problem Choosing the best model among many in different states of the world.
method Reinforcement learning algorithm to estimate optimal policy.
result Algorithm consistently selects optimal model based on covariates.
Adaptive Bayesian Optimization for resource-constrained experiments with switching costs.
problem Sequential experimental design with varying costs for changing design variables.
method Adapted batch algorithms to sequential problem, proposing cost-aware and cost-ignorant methods.
result Cost-aware algorithm outperforms tuned process-constrained algorithms in all settings considered.
New framework for policy gradient methods in continuous time reinforcement learning.
problem Addressing policy gradient methods for continuous time reinforcement learning.
method Control randomisation technique to derive policy gradient representation for various Markovian control problems.
result Demonstrated application to optimal switching problems in the energy sector.
The stochastic knapsack has been used as a model in wide ranging applications from dynamic resource allocation to admission control in telecommunication. In recent years, a variation of the model has become a basic tool in studying problems that arise in revenue management and dynamic/flexible pricing; and it is in thi…
Algorithm improves reinforcement learning policies using offline data.
problem Improving reinforcement learning policies with limited online data.
method Designs a single non-reactive policy using offline data with provable guarantees.
result Algorithm achieves better policy quality with less online data.
Algorithm for bandits with switching costs achieves optimal regret bounds.
problem Optimal regret bounds for stochastic and adversarial bandits with switching costs.
method Adaptation of Tsallis-INF algorithm with no prior knowledge of regime or time horizon.
result Achieves minimax optimal regret bounds in various settings.
We study online learning when partial feedback information is provided following every action of the learning process, and the learner incurs switching costs for changing his actions. In this setting, the feedback information system can be represented by a graph, and previous works studied the expected regret of the le…
SCaLE tackles dynamic regret in noisy bandit feedback with switching costs.
problem Unbounded metric movement costs in bandit online convex optimization.
method SCaLE algorithm for high-dimensional dynamic quadratic hitting costs and -norm switching costs, with spectral regret analysis.
result First algorithm achieving sub-linear dynamic regret without hitting cost knowledge.
OMGD algorithm optimizes online convex optimization with switching costs and delayed gradients.
problem Optimizing online convex optimization with switching costs and delayed gradients.
method Proposed an online multiple gradient descent (OMGD) algorithm for quadratic and linear switching costs.
result OMGD achieves optimal dynamic regret in the limited information setting.
The paper improves competitive and dynamic regret bounds for smoothed online learning.
problem Smoothed online learning with hitting and switching costs.
method Optimization problems to minimize hitting cost, dynamic regret modification of existing algorithms.
result Improved competitive and dynamic regret bounds for various function classes.
The paper develops RL methods for optimal switching between multiple states.
problem Optimal switching between multiple states in continuous time.
method Entropy-regularized exploration, HJB equations, policy improvement, value function convergence.
result The RL algorithm converges to optimal policies as temperature parameter vanishes.
This paper first describes a class of uncertain stochastic control systems with Markovian switching, and derives an Itô-Liu formula for Markov-modulated processes. And we characterize an optimal control law, which satisfies the generalized Hamilton-Jacobi-Bellman (HJB) equation with Markovian switching. Then, by using …
The present work studies and analyzes general defaultable OTC contract in presence of a contingent CSA, which is a theoretical counterparty risk mitigation mechanism of switching type that allows the counterparty of a general OTC contract to switch from zero to full/perfect collateralization and switch back whenever sh…
In this paper, we study optimal switching problems under ambiguity. To characterize the optimal switching under ambiguity in the finite horizon, we use multidimensional reflected backward stochastic differential equations (multidimensional RBSDEs) and show that a value function of the optimal switching under ambiguity …
Algorithm learns to switch control among agents in a team.
problem Learning to switch control among reinforcement learning agents.
method 2-layer Markov decision process, upper confidence bounds, shared confidence bounds.
result Sublinear total regret with shared confidence bounds.
New RL algorithm reduces deployment cost for linear function approximations.
problem Efficiently deploying new policies in RL with unknown rewards.
method Proposes an algorithm that minimizes trajectories needed for identifying optimal policies.
result Achieves optimal deployment complexity and sample complexity.
This paper analyzes the problem of starting and stopping a Cox-Ingersoll-Ross (CIR) process with fixed costs. In addition, we also study a related optimal switching problem that involves an infinite sequence of starts and stops. We establish the conditions under which the starting-stopping and switching problems admit …
Optimizes dividend payouts with fixed costs and regime switching.
problem Maximizing dividends with fixed transaction costs and regime switching.
method Identifies optimal dividend strategy as a two-barrier impulsive strategy.
result Explicit determination of optimal strategy for various drift and volatility scenarios.
This work models market regimes using CTMSTOU and simulates trading policies.
problem Defining and understanding market regimes in finance.
method Discrete event time multi-agent market simulation with CTMSTOU model.
result Illustrates the importance of regime-awareness in trading policies.
New DR-IC estimator reduces bias and variance in OPE.
problem Estimating value of a target policy using logged data from a different policy.
method DR-IC estimator that combines parametric reward model and context-based switching rule.
result DR-IC estimator outperforms state-of-the-art OPE algorithms.
Optimizes consumption under regime-switching economic states with risk-sensitive preferences.
problem Optimizing consumption in an economy with uncertain states and random shocks.
method Risk-sensitive optimization of consumption-utility with a Markov chain model of economic states and i.i.d. random shocks.
result Existence of unique optimal policy and value function in stationary policies.
We consider the classical stochastic multi-armed bandit problem with a constraint that limits the total cost incurred by switching between actions to be no larger than a given switching budget. For this problem, we prove matching upper and lower bounds on the optimal (i.e., minimax) regret, and provide efficient rate-o…
This paper is concerned with cost optimization of an insurance company. The surplus of the insurance company is modeled by a controlled regime switching diffusion, where the regime switching mechanism provides the fluctuations of the random environment. The goal is to find an optimal control that minimizes the total co…
New method reduces regret and communication costs in federated Q-learning.
problem Worst-case regret and communication cost bounds in federated Q-learning.
method Gap-dependent analysis leveraging MDP structures.
result Achieves -type regret and communication cost bounds.
In cellular systems, the user equipment (UE) can request a change in the frequency band when its rate drops below a threshold on the current band. The UE is then instructed by the base station (BS) to measure the quality of candidate bands, which requires a measurement gap in the data transmission, thus lowering the da…
Imitation learning (IL) consists of a set of tools that leverage expert demonstrations to quickly learn policies. However, if the expert is suboptimal, IL can yield policies with inferior performance compared to reinforcement learning (RL). In this paper, we aim to provide an algorithm that combines the best aspects of…
New algorithms tackle adversarial combinatorial bandits with switching costs.
problem Adversarial combinatorial bandits with switching costs.
method Design algorithms operating in batches to restrict switches, proving lower bounds and achieving upper bounds on regret.
result Achieved upper bounds on regret for both bandit and semi-bandit feedback settings.
Paper proves exponential lower bounds for policy iteration in MDPs.
problem Proving lower bounds for policy iteration in multi-action MDPs.
method Generalized previous results to k-action MDPs, constructed families of MDPs.
result Proved novel exponential lower bound of (3+k)2^(N/2-3) iterations.