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.
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.
168,695 papers · 148 categories
Trend · papers per month
48 results for “Policy Switching”
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.
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.
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…
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.
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.
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 …
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.
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.
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.
Reinforcement learning agents have been mostly developed and evaluated under the assumption that they will operate in a fully autonomous manner -- they will take all actions. In this work, our goal is to develop algorithms that, by learning to switch control between agents, allow existing reinforcement learning agents …
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.
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…
Efficient RL algorithms for linear function approximation with limited adaptivity constraints.
problem Limited adaptivity in reinforcement learning with linear function approximation.
method Proposed two efficient online RL algorithms for episodic linear Markov decision processes under batch learning and rare policy switch models.
result Achieved efficient regret bounds for both batch learning and rare policy switch models, with substantial reduction in adaptivity.
PCGS-TF uses a Transformer to adaptively control expert switching in non-stationary environments.
problem Static regret is insufficient for strictly online prediction in non-stationary settings.
method Policy-Controlled Generalized Share (PCGS) with a Transformer as an update controller.
result PCGS-TF achieves the lowest dynamic regret in non-stationary families and expert pools.
Motivated by recommendation problems in music streaming platforms, we propose a nonstationary stochastic bandit model in which the expected reward of an arm depends on the number of rounds that have passed since the arm was last pulled. After proving that finding an optimal policy is NP-hard even when all model paramet…
Excessively changing policies in many real world scenarios is difficult, unethical, or expensive. After all, doctor guidelines, tax codes, and price lists can only be reprinted so often. We may thus want to only change a policy when it is probable that the change is beneficial. In cases that a policy is a threshold on …
Two algorithms achieve optimal regret with limited adaptivity in multinomial logistic bandits.
problem Achieving optimal regret with limited adaptivity in multinomial logistic bandits.
method Presented two algorithms, B-MNL-CB and RS-MNL, for batched and rarely-switching paradigms.
result Achieved regret with limited adaptivity.
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.
H-ReIL learns to drive safely in near-accident scenarios.
problem Driving safely in high-risk near-accident situations.
method Hierarchical RL and IL approach.
result High-level policy switches between low-level policies for safe driving.
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 …
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 $O\left(d H\log K
ight)$.
The study classifies policy announcements' impact on stock market volatility.
problem Evaluating the impact of Central Bank announcements on stock market volatility.
method Proposed a model-based classification method using Markov Switching dynamics and Multiplicative Error Model.
result Successful classification of 144 European Central Bank announcements on stock market volatility.
In this paper, we consider the optimal dividend problem for a company. We describe the surplus process of the company by a diffusion model with regime switching. The aim of the company is to choose a dividend policy to maximize the expected total discounted payments until ruin. In this article, we consider a hybrid div…
Study indifference pricing for insurance policies in a regime-switching market model.
problem Indifference pricing of pure endowment policies in a stochastic-factor model with different economic regimes.
method Stochastic control approach based on Hamilton-Jacobi-Bellman equation, Feynman-Kac formula, and sensitivity analysis.
result Characterization of indifference price as a solution to a linear PDE and a backward PDE.
We develop a robust RL algorithm for off-dynamics environments with improved suboptimality bounds and computational efficiency.
problem Learning policies robust to uncertainties in transition dynamics between training and deployment environments.
method Distributionally robust Markov decision processes (DRMDPs) with a novel algorithm We-DRIVE-U.
result Improved suboptimality bound of , near-optimal up to .
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.
Optimal dividends strategy in a two-state regime-switching environment.
problem Maximizing profits from dividends until bankruptcy in a company with fluctuating cash surplus and regime changes in drift, volatility, and bankruptcy levels.
method Analyzes the optimal dividend payout strategy considering four factors: Brownian fluctuations in cash surplus, regime changes in drift, volatility, and bankruptcy levels.
result Rich structure of the optimal strategy, which can be either barrier-type or liquidation-barrier type, depending on model parameters.
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…
In a continuous time stochastic economy, this paper considers the problem of consumption and investment in a financial market in which the representative investor exhibits a change in the discount rate. The investment opportunities are a stock and a riskless account. The market coefficients and discount factor switches…
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.
In this paper we treat a gas storage valuation problem as a Markov Decision Process. As opposed to existing literature we model the gas price process as a regime-switching model. Such a model has shown to fit market data quite well in Chen and Forsyth (2010). Before we apply a numerical algorithm to solve the problem, …
Explicit Solutions of Optimal Consumption, Investment and Insurance Problem with Regime Switchingq-fin.RM
We consider an investor who wants to select her/his optimal consumption, investment and insurance policies. Motivated by new insurance products, we allow not only the financial marke but also the insurable loss to depend on the regime of the economy. The objective of the investor is to maximize her/his expected total d…
MA-COPP predicts multi-agent system outcomes using data from a different policy, with probabilistic guarantees.
problem Predicting outcomes in multi-agent systems using data from a different policy.
method Conformal prediction framework applied to multi-agent systems, avoiding exhaustive search.
result Achieves probabilistic guarantees for multi-agent system predictions.
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 …
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.
Reinforcement learning is a promising approach to synthesizing policies for challenging robotics tasks. A key problem is how to ensure safety of the learned policy---e.g., that a walking robot does not fall over or that an autonomous car does not run into an obstacle. We focus on the setting where the dynamics are know…
Examining the Effect of Monetary Policy and Monetary Policy Uncertainty on Cryptocurrencies Marketq-fin.ST
Study finds monetary policy uncertainty negatively impacts Bitcoin returns.
problem Impact of monetary policy and uncertainty on cryptocurrencies market.
method Markov Switching Means VAR (MSM-VAR) method.
result Monetary policy uncertainty leads to a decline in Bitcoin returns.
This paper proposes a general framework of multi-armed bandit (MAB) processes by introducing a type of restrictions on the switches among arms evolving in continuous time. The Gittins index process is constructed for any single arm subject to the restrictions on switches and then the optimality of the corresponding Git…
New method optimizes policies in non-stationary environments.
problem Optimizing policies in non-stationary, context-dependent environments.
method Two-phase approach: offline learning and online adaptation.
result Our method outperforms existing approaches in both synthetic and real-world datasets.
Optimized portfolio management with dynamic market regimes using RL and OC learning.
problem Mean-Variance portfolio optimization in a regime-switching market.
method Reinforcement learning (RL) with Orthogonality Condition (OC) learning for regime-switching market dynamics.
result OC learning outperforms TD learning in simulated and real market scenarios, leading to better portfolio performance.
Policy iteration is a family of algorithms that are used to find an optimal policy for a given Markov Decision Problem (MDP). Simple Policy iteration (SPI) is a type of policy iteration where the strategy is to change the policy at exactly one improvable state at every step. Melekopoglou and Condon [1990] showed an exp…
New actor-critic algorithm achieves optimal sample efficiency in RL.
problem Achieving -optimal policies with minimal samples in RL.
method Integrates optimism, off-policy critic estimation, and rare-switching policy resets.
result Sample complexity of trajectories.