PyTorchKR Papers

최신 논문

총 1,810편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2502.01268

Resilient UAV Trajectory Planning via Few-Shot Meta-Offline Reinforcement Learning

Reinforcement learning (RL) has been a promising essence in future 5G-beyond and 6G systems. Its main advantage lies in its robust model-free decision-making in complex and large-dimension wireless environments. However, most existing RL frameworks rely on online interaction with the environment, which might not be feasible due to safety and cost concerns. Another problem with online RL is the lack of scalability of the designed algorithm with dynamic or new environments. This work proposes a novel, resilient, few-shot meta-offline RL algorithm combining offline RL using conservative Q-learning (CQL) and meta-learning using model-agnostic meta-learning (MAML). The proposed algorithm can train RL models using static offline datasets without any online interaction with the environments. In addition, with the aid of MAML, the proposed model can be scaled up to new unseen environments. We showcase the proposed algorithm for optimizing an unmanned aerial vehicle (UAV) 's trajectory and scheduling policy to minimize the age-of-information (AoI) and transmission power of limited-power devices. Numerical results show that the proposed few-shot meta-offline RL algorithm converges faster than baseline schemes, such as deep Q-networks and CQL. In addition, it is the only algorithm that can achieve optimal joint AoI and transmission power using an offline dataset with few shots of data points and is resilient to network failures due to unprecedented environmental changes.

arXiv:2502.00288

Learning from Suboptimal Data in Continuous Control via Auto-Regressive Soft Q-Network

Reinforcement learning (RL) for continuous control often requires large amounts of online interaction data. Value-based RL methods can mitigate this burden by offering relatively high sample efficiency. Some studies further enhance sample efficiency by incorporating offline demonstration data to "kick-start" training, achieving promising results in continuous control. However, they typically compute the Q-function independently for each action dimension, neglecting interdependencies and making it harder to identify optimal actions when learning from suboptimal data, such as non-expert demonstration and online-collected data during the training process. To address these issues, we propose Auto-Regressive Soft Q-learning (ARSQ), a value-based RL algorithm that models Q-values in a coarse-to-fine, auto-regressive manner. First, ARSQ decomposes the continuous action space into discrete spaces in a coarse-to-fine hierarchy, enhancing sample efficiency for fine-grained continuous control tasks. Next, it auto-regressively predicts dimensional action advantages within each decision step, enabling more effective decision-making in continuous control tasks. We evaluate ARSQ on two continuous control benchmarks, RLBench and D4RL, integrating demonstration data into online training. On D4RL, which includes non-expert demonstrations, ARSQ achieves an average $1.62\times$ performance improvement over SOTA value-based baseline. On RLBench, which incorporates expert demonstrations, ARSQ surpasses various baselines, demonstrating its effectiveness in learning from suboptimal online-collected data. Project page is at https://sites.google.com/view/ar-soft-q

arXiv:2501.19254

Linear $Q$-Learning Does Not Diverge: Convergence Rates to a Bounded Set

$Q$-learning is one of the most fundamental reinforcement learning algorithms. Previously, it is widely believed that $Q$-learning with linear function approximation (i.e., linear $Q$-learning) suffers from possible divergence. This paper instead establishes the first $L^2$ convergence rate of linear $Q$-learning to a bounded set. Notably, we do not make any modification to the original linear $Q$-learning algorithm, do not make any Bellman completeness assumption, and do not make any near-optimality assumption on the behavior policy. All we need is an $\epsilon$-softmax behavior policy with an adaptive temperature. The key to our analysis is the general result of stochastic approximations under Markovian noise with fast-changing transition functions. As a side product, we also use this general result to establish the $L^2$ convergence rate of tabular $Q$-learning with an $\epsilon$-softmax behavior policy, for which we rely on a novel pseudo-contraction property of the weighted Bellman optimality operator.

arXiv:2501.16509

Reinforcement Learning for Quantum Circuit Design: Using Matrix Representations

Quantum computing promises advantages over classical computing. The manufacturing of quantum hardware is in the infancy stage, called the Noisy Intermediate-Scale Quantum (NISQ) era. A major challenge is automated quantum circuit design that map a quantum circuit to gates in a universal gate set. In this paper, we present a generic MDP modeling and employ Q-learning and DQN algorithms for quantum circuit design. By leveraging the power of deep reinforcement learning, we aim to provide an automatic and scalable approach over traditional hand-crafted heuristic methods.

arXiv:2501.15304

Music Generation using Human-In-The-Loop Reinforcement Learning

This paper presents an approach that combines Human-In-The-Loop Reinforcement Learning (HITL RL) with principles derived from music theory to facilitate real-time generation of musical compositions. HITL RL, previously employed in diverse applications such as modelling humanoid robot mechanics and enhancing language models, harnesses human feedback to refine the training process. In this study, we develop a HILT RL framework that can leverage the constraints and principles in music theory. In particular, we propose an episodic tabular Q-learning algorithm with an epsilon-greedy exploration policy. The system generates musical tracks (compositions), continuously enhancing its quality through iterative human-in-the-loop feedback. The reward function for this process is the subjective musical taste of the user.

arXiv:2501.14199

Coordinating Ride-Pooling with Public Transit using Reward-Guided Conservative Q-Learning: An Offline Training and Online Fine-Tuning Reinforcement Learning Framework

This paper introduces a novel reinforcement learning (RL) framework, termed Reward-Guided Conservative Q-learning (RG-CQL), to enhance coordination between ride-pooling and public transit within a multimodal transportation network. We model each ride-pooling vehicle as an agent governed by a Markov Decision Process (MDP) and propose an offline training and online fine-tuning RL framework to learn the optimal operational decisions of the multimodal transportation systems, including rider-vehicle matching, selection of drop-off locations for passengers, and vehicle routing decisions, with improved data efficiency. During the offline training phase, we develop a Conservative Double Deep Q Network (CDDQN) as the action executor and a supervised learning-based reward estimator, termed the Guider Network, to extract valuable insights into action-reward relationships from data batches. In the online fine-tuning phase, the Guider Network serves as an exploration guide, aiding CDDQN in effectively and conservatively exploring unknown state-action pairs. The efficacy of our algorithm is demonstrated through a realistic case study using real-world data from Manhattan. We show that integrating ride-pooling with public transit outperforms two benchmark cases solo rides coordinated with transit and ride-pooling without transit coordination by 17% and 22% in the achieved system rewards, respectively. Furthermore, our innovative offline training and online fine-tuning framework offers a remarkable 81.3% improvement in data efficiency compared to traditional online RL methods with adequate exploration budgets, with a 4.3% increase in total rewards and a 5.6% reduction in overestimation errors. Experimental results further demonstrate that RG-CQL effectively addresses the challenges of transitioning from offline to online RL in large-scale ride-pooling systems integrated with transit.

arXiv:2501.13448

BMG-Q: Localized Bipartite Match Graph Attention Q-Learning for Ride-Pooling Order Dispatch

This paper introduces Localized Bipartite Match Graph Attention Q-Learning (BMG-Q), a novel Multi-Agent Reinforcement Learning (MARL) algorithm framework tailored for ride-pooling order dispatch. BMG-Q advances ride-pooling decision-making process with the localized bipartite match graph underlying the Markov Decision Process, enabling the development of novel Graph Attention Double Deep Q Network (GATDDQN) as the MARL backbone to capture the dynamic interactions among ride-pooling vehicles in fleet. Our approach enriches the state information for each agent with GATDDQN by leveraging a localized bipartite interdependence graph and enables a centralized global coordinator to optimize order matching and agent behavior using Integer Linear Programming (ILP). Enhanced by gradient clipping and localized graph sampling, our GATDDQN improves scalability and robustness. Furthermore, the inclusion of a posterior score function in the ILP captures the online exploration-exploitation trade-off and reduces the potential overestimation bias of agents, thereby elevating the quality of the derived solutions. Through extensive experiments and validation, BMG-Q has demonstrated superior performance in both training and operations for thousands of vehicle agents, outperforming benchmark reinforcement learning frameworks by around 10% in accumulative rewards and showing a significant reduction in overestimation bias by over 50%. Additionally, it maintains robustness amidst task variations and fleet size changes, establishing BMG-Q as an effective, scalable, and robust framework for advancing ride-pooling order dispatch operations.

arXiv:2501.10243

Random-Key Algorithms for Optimizing Integrated Operating Room Scheduling

Efficient surgery room scheduling is essential for hospital efficiency, patient satisfaction, and resource utilization. This study addresses this challenge by introducing a novel concept of Random-Key Optimizer (RKO), rigorously tested on literature and new, real-world inspired instances. Our combinatorial optimization problem incorporates multi-room scheduling, equipment scheduling, and complex availability constraints for rooms, patients, and surgeons, facilitating rescheduling and enhancing operational flexibility. The RKO approach represents solutions as points in a continuous space, which are then mapped in the problem solution space via a deterministic function known as a decoder. The core idea is to operate metaheuristics and heuristics in the random-key space, unaware of the original solution space. We design the Biased Random-Key Genetic Algorithm with $Q$-Learning, Simulated Annealing, and Iterated Local Search for use within an RKO framework, employing a single decoder function. The proposed metaheuristics are complemented by lower-bound formulations, providing optimal gaps for evaluating the effectiveness of the heuristic results. Our results demonstrate significant lower and upper bounds improvements for the literature instances, notably proving one optimal result. Furthermore, the best-proposed metaheuristic efficiently generates schedules for the newly introduced instances, even in highly constrained scenarios. This research offers valuable insights and practical solutions for improving surgery scheduling processes, offering tangible benefits to hospitals by optimising resource allocation, reducing patient wait times, and enhancing overall operational efficiency.

arXiv:2501.06510

Cooperative Optimal Output Tracking for Discrete-Time Multiagent Systems: Stabilizing Policy Iteration Frameworks and Analysis

In this paper, two model-free optimal output tracking frameworks based on policy iteration for discrete-time multi-agent systems are proposed. First, we establish a framework of stabilizing policy iteration that can start from any initial feedback control policy, relaxing the dependence of traditional policy iteration on the initial stabilizing control policy. Then, another efficient and equivalent $Q$-learning policy iteration framework is developed, which is shown to require only less system data to get the same results as the stabilizing policy iteration. Both frameworks obtain stabilizing control policy by iterating the stabilizing virtual closed-loop system step-by-step to the actual closed-loop system. Multiple explicit schemes for the iteration step-size/coefficient are designed and their stability during the above iterations is analyzed. By using the generated closed-loop stabilizing control policy and two frameworks, the optimal feedback control gain is obtained. The approximate solution of the regulator equations is found by model-free iteration, which leads to the optimal feedforward gain. Finally, the cooperative optimal output tracking is realized by a distributed feedforward-feedback controller. The proposed algorithms are validated by simulation.

arXiv:2501.08669

SPEQ: Stabilization Phases for Efficient Q-Learning in High Update-To-Data Ratio Reinforcement Learning

A key challenge in Deep Reinforcement Learning is sample efficiency, especially in real-world applications where collecting environment interactions is expensive or risky. Recent off-policy algorithms improve sample efficiency by increasing the Update-To-Data (UTD) ratio and performing more gradient updates per environment interaction. While this improves sample efficiency, it significantly increases computational cost due to the higher number of gradient updates required. In this paper we propose a sample-efficient method to improve computational efficiency by separating training into distinct learning phases in order to exploit gradient updates more effectively. Our approach builds on top of the Dropout Q-Functions (DroQ) algorithm and alternates between an online, low UTD ratio training phase, and an offline stabilization phase. During the stabilization phase, we fine-tune the Q-functions without collecting new environment interactions. This process improves the effectiveness of the replay buffer and reduces computational overhead. Our experimental results on continuous control problems show that our method achieves results comparable to state-of-the-art, high UTD ratio algorithms while requiring 56\% fewer gradient updates and 50\% less training time than DroQ. Our approach offers an effective and computationally economical solution while maintaining the same sample efficiency as the more costly, high UTD ratio state-of-the-art.

arXiv:2501.08907

Projection Implicit Q-Learning with Support Constraint for Offline Reinforcement Learning

Offline Reinforcement Learning (RL) faces a critical challenge of extrapolation errors caused by out-of-distribution (OOD) actions. Implicit Q-Learning (IQL) algorithm employs expectile regression to achieve in-sample learning, effectively mitigating the risks associated with OOD actions. However, the fixed hyperparameter in policy evaluation and density-based policy improvement method limit its overall efficiency. In this paper, we propose Proj-IQL, a projective IQL algorithm enhanced with the support constraint. In the policy evaluation phase, Proj-IQL generalizes the one-step approach to a multi-step approach through vector projection, while maintaining in-sample learning and expectile regression framework. In the policy improvement phase, Proj-IQL introduces support constraint that is more aligned with the policy evaluation approach. Furthermore, we theoretically demonstrate that Proj-IQL guarantees monotonic policy improvement and enjoys a progressively more rigorous criterion for superior actions. Empirical results demonstrate the Proj-IQL achieves state-of-the-art performance on D4RL benchmarks, especially in challenging navigation domains.

arXiv:2501.08109

Data-driven inventory management for new products: An adjusted Dyna-$Q$ approach with transfer learning

In this paper, we propose a novel reinforcement learning algorithm for inventory management of newly launched products with no historical demand information. The algorithm follows the classic Dyna-$Q$ structure, balancing the model-free and model-based approaches, while accelerating the training process of Dyna-$Q$ and mitigating the model discrepancy generated by the model-based feedback. Based on the idea of transfer learning, warm-start information from the demand data of existing similar products can be incorporated into the algorithm to further stabilize the early-stage training and reduce the variance of the estimated optimal policy. Our approach is validated through a case study of bakery inventory management with real data. The adjusted Dyna-$Q$ shows up to a 23.7\% reduction in average daily cost compared with $Q$-learning, and up to a 77.5\% reduction in training time within the same horizon compared with classic Dyna-$Q$. By using transfer learning, it can be found that the adjusted Dyna-$Q$ has the lowest total cost, lowest variance in total cost, and relatively low shortage percentages among all the benchmarking algorithms under a 30-day testing.

arXiv:2501.06937공식 코드 · Papers with Code

An Empirical Study of Deep Reinforcement Learning in Continuing Tasks

In reinforcement learning (RL), continuing tasks refer to tasks where the agent-environment interaction is ongoing and can not be broken down into episodes. These tasks are suitable when environment resets are unavailable, agent-controlled, or predefined but where all rewards-including those beyond resets-are critical. These scenarios frequently occur in real-world applications and can not be modeled by episodic tasks. While modern deep RL algorithms have been extensively studied and well understood in episodic tasks, their behavior in continuing tasks remains underexplored. To address this gap, we provide an empirical study of several well-known deep RL algorithms using a suite of continuing task testbeds based on Mujoco and Atari environments, highlighting several key insights concerning continuing tasks. Using these testbeds, we also investigate the effectiveness of a method for improving temporal-difference-based RL algorithms in continuing tasks by centering rewards, as introduced by Naik et al. (2024). While their work primarily focused on this method in conjunction with Q-learning, our results extend their findings by demonstrating that this method is effective across a broader range of algorithms, scales to larger tasks, and outperforms two other reward-centering approaches.

arXiv:2501.07445

Online inductive learning from answer sets for efficient reinforcement learning exploration

This paper presents a novel approach combining inductive logic programming with reinforcement learning to improve training performance and explainability. We exploit inductive learning of answer set programs from noisy examples to learn a set of logical rules representing an explainable approximation of the agent policy at each batch of experience. We then perform answer set reasoning on the learned rules to guide the exploration of the learning agent at the next batch, without requiring inefficient reward shaping and preserving optimality with soft bias. The entire procedure is conducted during the online execution of the reinforcement learning algorithm. We preliminarily validate the efficacy of our approach by integrating it into the Q-learning algorithm for the Pac-Man scenario in two maps of increasing complexity. Our methodology produces a significant boost in the discounted return achieved by the agent, even in the first batches of training. Moreover, inductive learning does not compromise the computational time required by Q-learning and learned rules quickly converge to an explanation of the agent policy.

arXiv:2501.04870

Deep Transfer $Q$-Learning for Offline Non-Stationary Reinforcement Learning

In dynamic decision-making scenarios across business and healthcare, leveraging sample trajectories from diverse populations can significantly enhance reinforcement learning (RL) performance for specific target populations, especially when sample sizes are limited. While existing transfer learning methods primarily focus on linear regression settings, they lack direct applicability to reinforcement learning algorithms. This paper pioneers the study of transfer learning for dynamic decision scenarios modeled by non-stationary finite-horizon Markov decision processes, utilizing neural networks as powerful function approximators and backward inductive learning. We demonstrate that naive sample pooling strategies, effective in regression settings, fail in Markov decision processes.To address this challenge, we introduce a novel ``re-weighted targeting procedure'' to construct ``transferable RL samples'' and propose ``transfer deep $Q^*$-learning'', enabling neural network approximation with theoretical guarantees. We assume that the reward functions are transferable and deal with both situations in which the transition densities are transferable or nontransferable. Our analytical techniques for transfer learning in neural network approximation and transition density transfers have broader implications, extending to supervised transfer learning with neural networks and domain shift scenarios. Empirical experiments on both synthetic and real datasets corroborate the advantages of our method, showcasing its potential for improving decision-making through strategically constructing transferable RL samples in non-stationary reinforcement learning contexts.

arXiv:2501.00068

Dynamic Optimization of Storage Systems Using Reinforcement Learning Techniques

The exponential growth of data-intensive applications has placed unprecedented demands on modern storage systems, necessitating dynamic and efficient optimization strategies. Traditional heuristics employed for storage performance optimization often fail to adapt to the variability and complexity of contemporary workloads, leading to significant performance bottlenecks and resource inefficiencies. To address these challenges, this paper introduces RL-Storage, a novel reinforcement learning (RL)-based framework designed to dynamically optimize storage system configurations. RL-Storage leverages deep Q-learning algorithms to continuously learn from real-time I/O patterns and predict optimal storage parameters, such as cache size, queue depths, and readahead settings[1]. The proposed framework operates within the storage kernel, ensuring minimal latency and low computational overhead. Through an adaptive feedback mechanism, RL-Storage dynamically adjusts critical parameters, achieving efficient resource utilization across a wide range of workloads. Experimental evaluations conducted on a range of benchmarks, including RocksDB and PostgreSQL, demonstrate significant improvements, with throughput gains of up to 2.6x and latency reductions of 43% compared to baseline heuristics. Additionally, RL-Storage achieves these performance enhancements with a negligible CPU overhead of 0.11% and a memory footprint of only 5 KB, making it suitable for seamless deployment in production environments. This work underscores the transformative potential of reinforcement learning techniques in addressing the dynamic nature of modern storage systems. By autonomously adapting to workload variations in real time, RL-Storage provides a robust and scalable solution for optimizing storage performance, paving the way for next-generation intelligent storage infrastructures.

arXiv:2501.00913

$β$-DQN: Improving Deep Q-Learning By Evolving the Behavior

While many sophisticated exploration methods have been proposed, their lack of generality and high computational cost often lead researchers to favor simpler methods like $\epsilon$-greedy. Motivated by this, we introduce $\beta$-DQN, a simple and efficient exploration method that augments the standard DQN with a behavior function $\beta$. This function estimates the probability that each action has been taken at each state. By leveraging $\beta$, we generate a population of diverse policies that balance exploration between state-action coverage and overestimation bias correction. An adaptive meta-controller is designed to select an effective policy for each episode, enabling flexible and explainable exploration. $\beta$-DQN is straightforward to implement and adds minimal computational overhead to the standard DQN. Experiments on both simple and challenging exploration domains show that $\beta$-DQN outperforms existing baseline methods across a wide range of tasks, providing an effective solution for improving exploration in deep reinforcement learning.

arXiv:2412.20845

Data-Based Efficient Off-Policy Stabilizing Optimal Control Algorithms for Discrete-Time Linear Systems via Damping Coefficients

Policy iteration is one of the classical frameworks of reinforcement learning, which requires a known initial stabilizing control. However, finding the initial stabilizing control depends on the known system model. To relax this requirement and achieve model-free optimal control, in this paper, two different reinforcement learning algorithms based on policy iteration and variable damping coefficients are designed for unknown discrete-time linear systems. First, a stable artificial system is designed, and this system is gradually iterated to the original system by varying the damping coefficients. This allows the initial stabilizing control to be obtained in a finite number of iteration steps. Then, an off-policy iteration algorithm and an off-policy $\mathcal{Q}$-learning algorithm are designed to select the appropriate damping coefficients and realize data-driven. In these two algorithms, the current estimates of optimal control gain are not applied to the system to re-collect data. Moreover, they are characterized by the fast convergence of the traditional policy iteration. Finally, the proposed algorithms are validated by simulation.

arXiv:2412.19835

Multi-Agent Q-Learning for Real-Time Load Balancing User Association and Handover in Mobile Networks

As next generation cellular networks become denser, associating users with the optimal base stations at each time while ensuring no base station is overloaded becomes critical for achieving stable and high network performance. We propose multi-agent online Q-learning (QL) algorithms for performing real-time load balancing user association and handover in dense cellular networks. The load balancing constraints at all base stations couple the actions of user agents, and we propose two multi-agent action selection policies, one centralized and one distributed, to satisfy load balancing at every learning step. In the centralized policy, the actions of UEs are determined by a central load balancer (CLB) running an algorithm based on swapping the worst connection to maximize the total learning reward. In the distributed policy, each UE takes an action based on its local information by participating in a distributed matching game with the BSs to maximize the local reward. We then integrate these action selection policies into an online QL algorithm that adapts in real-time to network dynamics including channel variations and user mobility, using a reward function that considers a handover cost to reduce handover frequency. The proposed multi-agent QL algorithm features low-complexity and fast convergence, outperforming 3GPP max-SINR association. Both policies adapt well to network dynamics at various UE speed profiles from walking, running, to biking and suburban driving, illustrating their robustness and real-time adaptability.

arXiv:2412.20329

Protein Structure Prediction in the 3D HP Model Using Deep Reinforcement Learning

We address protein structure prediction in the 3D Hydrophobic-Polar lattice model through two novel deep learning architectures. For proteins under 36 residues, our hybrid reservoir-based model combines fixed random projections with trainable deep layers, achieving optimal conformations with 25% fewer training episodes. For longer sequences, we employ a long short-term memory network with multi-headed attention, matching best-known energy values. Both architectures leverage a stabilized Deep Q-Learning framework with experience replay and target networks, demonstrating consistent achievement of optimal conformations while significantly improving training efficiency compared to existing methods.