PyTorchKR Papers

최신 논문

총 13,745편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2501.15603

Advancing TDFN: Precise Fixation Point Generation Using Reconstruction Differences

Wang and Wang (2025) proposed the Task-Driven Fixation Network (TDFN) based on the fixation mechanism, which leverages low-resolution information along with high-resolution details near fixation points to accomplish specific visual tasks. The model employs reinforcement learning to generate fixation points. However, training reinforcement learning models is challenging, particularly when aiming to generate pixel-level accurate fixation points on high-resolution images. This paper introduces an improved fixation point generation method by leveraging the difference between the reconstructed image and the input image to train the fixation point generator. This approach directs fixation points to areas with significant differences between the reconstructed and input images. Experimental results demonstrate that this method achieves highly accurate fixation points, significantly enhances the network's classification accuracy, and reduces the average number of required fixations to achieve a predefined accuracy level.

arXiv:2501.15495공식 코드 · Papers with Code

Expert-Free Online Transfer Learning in Multi-Agent Reinforcement Learning

Reinforcement Learning (RL) enables an intelligent agent to optimise its performance in a task by continuously taking action from an observed state and receiving a feedback from the environment in form of rewards. RL typically uses tables or linear approximators to map state-action tuples that maximises the reward. Combining RL with deep neural networks (DRL) significantly increases its scalability and enables it to address more complex problems than before. However, DRL also inherits downsides from both RL and deep learning. Despite DRL improves generalisation across similar state-action pairs when compared to simpler RL policy representations like tabular methods, it still requires the agent to adequately explore the state-action space. Additionally, deep methods require more training data, with the volume of data escalating with the complexity and size of the neural network. As a result, deep RL requires a long time to collect enough agent-environment samples and to successfully learn the underlying policy. Furthermore, often even a slight alteration to the task invalidates any previous acquired knowledge. To address these shortcomings, Transfer Learning (TL) has been introduced, which enables the use of external knowledge from other tasks or agents to enhance a learning process. The goal of TL is to reduce the learning complexity for an agent dealing with an unfamiliar task by simplifying the exploration process. This is achieved by lowering the amount of new information required by its learning model, resulting in a reduced overall convergence time...

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:2501.15085

Data Center Cooling System Optimization Using Offline Reinforcement Learning

The recent advances in information technology and artificial intelligence have fueled a rapid expansion of the data center (DC) industry worldwide, accompanied by an immense appetite for electricity to power the DCs. In a typical DC, around 30~40% of the energy is spent on the cooling system rather than on computer servers, posing a pressing need for developing new energy-saving optimization technologies for DC cooling systems. However, optimizing such real-world industrial systems faces numerous challenges, including but not limited to a lack of reliable simulation environments, limited historical data, and stringent safety and control robustness requirements. In this work, we present a novel physics-informed offline reinforcement learning (RL) framework for energy efficiency optimization of DC cooling systems. The proposed framework models the complex dynamical patterns and physical dependencies inside a server room using a purposely designed graph neural network architecture that is compliant with the fundamental time-reversal symmetry. Because of its well-behaved and generalizable state-action representations, the model enables sample-efficient and robust latent space offline policy learning using limited real-world operational data. Our framework has been successfully deployed and verified in a large-scale production DC for closed-loop control of its air-cooling units (ACUs). We conducted a total of 2000 hours of short and long-term experiments in the production DC environment. The results show that our method achieves 14~21% energy savings in the DC cooling system, without any violation of the safety or operational constraints. Our results have demonstrated the significant potential of offline RL in solving a broad range of data-limited, safety-critical real-world industrial control problems.

arXiv:2501.15034공식 코드 · Papers with Code

Divergence-Augmented Policy Optimization

In deep reinforcement learning, policy optimization methods need to deal with issues such as function approximation and the reuse of off-policy data. Standard policy gradient methods do not handle off-policy data well, leading to premature convergence and instability. This paper introduces a method to stabilize policy optimization when off-policy data are reused. The idea is to include a Bregman divergence between the behavior policy that generates the data and the current policy to ensure small and safe policy updates with off-policy data. The Bregman divergence is calculated between the state distributions of two policies, instead of only on the action probabilities, leading to a divergence augmentation formulation. Empirical experiments on Atari games show that in the data-scarce scenario where the reuse of off-policy data becomes necessary, our method can achieve better performance than other state-of-the-art deep reinforcement learning algorithms.

arXiv:2501.16288공식 코드 · Papers with Code

Upside Down Reinforcement Learning with Policy Generators

Upside Down Reinforcement Learning (UDRL) is a promising framework for solving reinforcement learning problems which focuses on learning command-conditioned policies. In this work, we extend UDRL to the task of learning a command-conditioned generator of deep neural network policies. We accomplish this using Hypernetworks - a variant of Fast Weight Programmers, which learn to decode input commands representing a desired expected return into command-specific weight matrices. Our method, dubbed Upside Down Reinforcement Learning with Policy Generators (UDRLPG), streamlines comparable techniques by removing the need for an evaluator or critic to update the weights of the generator. To counteract the increased variance in last returns caused by not having an evaluator, we decouple the sampling probability of the buffer from the absolute number of policies in it, which, together with a simple weighting strategy, improves the empirical convergence of the algorithm. Compared with existing algorithms, UDRLPG achieves competitive performance and high returns, sometimes outperforming more complex architectures. Our experiments show that a trained generator can generalize to create policies that achieve unseen returns zero-shot. The proposed method appears to be effective in mitigating some of the challenges associated with learning highly multimodal functions. Altogether, we believe that UDRLPG represents a promising step forward in achieving greater empirical sample efficiency in RL. A full implementation of UDRLPG is publicly available at https://github.com/JacopoD/udrlpg_

arXiv:2501.16142

Towards General-Purpose Model-Free Reinforcement Learning

Reinforcement learning (RL) promises a framework for near-universal problem-solving. In practice however, RL algorithms are often tailored to specific benchmarks, relying on carefully tuned hyperparameters and algorithmic choices. Recently, powerful model-based RL methods have shown impressive general results across benchmarks but come at the cost of increased complexity and slow run times, limiting their broader applicability. In this paper, we attempt to find a unifying model-free deep RL algorithm that can address a diverse class of domains and problem settings. To achieve this, we leverage model-based representations that approximately linearize the value function, taking advantage of the denser task objectives used by model-based RL while avoiding the costs associated with planning or simulated trajectories. We evaluate our algorithm, MR.Q, on a variety of common RL benchmarks with a single set of hyperparameters and show a competitive performance against domain-specific and general baselines, providing a concrete step towards building general-purpose model-free deep RL algorithms.

arXiv:2501.15928

Generative AI for Lyapunov Optimization Theory in UAV-based Low-Altitude Economy Networking

Lyapunov optimization theory has recently emerged as a powerful mathematical framework for solving complex stochastic optimization problems by transforming long-term objectives into a sequence of real-time short-term decisions while ensuring system stability. This theory is particularly valuable in unmanned aerial vehicle (UAV)-based low-altitude economy (LAE) networking scenarios, where it could effectively address inherent challenges of dynamic network conditions, multiple optimization objectives, and stability requirements. Recently, generative artificial intelligence (GenAI) has garnered significant attention for its unprecedented capability to generate diverse digital content. Extending beyond content generation, in this paper, we propose a framework integrating generative diffusion models with reinforcement learning to address Lyapunov optimization problems in UAV-based LAE networking. We begin by introducing the fundamentals of Lyapunov optimization theory and analyzing the limitations of both conventional methods and traditional AI-enabled approaches. We then examine various GenAI models and comprehensively analyze their potential contributions to Lyapunov optimization. Subsequently, we develop a Lyapunov-guided generative diffusion model-based reinforcement learning framework and validate its effectiveness through a UAV-based LAE networking case study. Finally, we outline several directions for future research.

arXiv:2501.15695

Contextual Knowledge Sharing in Multi-Agent Reinforcement Learning with Decentralized Communication and Coordination

Decentralized Multi-Agent Reinforcement Learning (Dec-MARL) has emerged as a pivotal approach for addressing complex tasks in dynamic environments. Existing Multi-Agent Reinforcement Learning (MARL) methodologies typically assume a shared objective among agents and rely on centralized control. However, many real-world scenarios feature agents with individual goals and limited observability of other agents, complicating coordination and hindering adaptability. Existing Dec-MARL strategies prioritize either communication or coordination, lacking an integrated approach that leverages both. This paper presents a novel Dec-MARL framework that integrates peer-to-peer communication and coordination, incorporating goal-awareness and time-awareness into the agents' knowledge-sharing processes. Our framework equips agents with the ability to (i) share contextually relevant knowledge to assist other agents, and (ii) reason based on information acquired from multiple agents, while considering their own goals and the temporal context of prior knowledge. We evaluate our approach through several complex multi-agent tasks in environments with dynamically appearing obstacles. Our work demonstrates that incorporating goal-aware and time-aware knowledge sharing significantly enhances overall performance.

arXiv:2501.14394

Reinforcement Learning for Efficient Returns Management

In retail warehouses, returned products are typically placed in an intermediate storage until a decision regarding further shipment to stores is made. The longer products are held in storage, the higher the inefficiency and costs of the returns management process, since enough storage area has to be provided and maintained while the products are not placed for sale. To reduce the average product storage time, we consider an alternative solution where reallocation decisions for products can be made instantly upon their arrival in the warehouse allowing only a limited number of products to still be stored simultaneously. We transfer the problem to an online multiple knapsack problem and propose a novel reinforcement learning approach to pack the items (products) into the knapsacks (stores) such that the overall value (expected revenue) is maximized. Empirical evaluations on simulated data demonstrate that, compared to the usual offline decision procedure, our approach comes with a performance gap of only 3% while significantly reducing the average storage time of a product by 96%.

arXiv:2501.14176

RL + Transformer = A General-Purpose Problem Solver

What if artificial intelligence could not only solve problems for which it was trained but also learn to teach itself to solve new problems (i.e., meta-learn)? In this study, we demonstrate that a pre-trained transformer fine-tuned with reinforcement learning over multiple episodes develops the ability to solve problems that it has never encountered before - an emergent ability called In-Context Reinforcement Learning (ICRL). This powerful meta-learner not only excels in solving unseen in-distribution environments with remarkable sample efficiency, but also shows strong performance in out-of-distribution environments. In addition, we show that it exhibits robustness to the quality of its training data, seamlessly stitches together behaviors from its context, and adapts to non-stationary environments. These behaviors demonstrate that an RL-trained transformer can iteratively improve upon its own solutions, making it an excellent general-purpose problem solver.

arXiv:2501.14122

Reinforcement Learning Platform for Adversarial Black-box Attacks with Custom Distortion Filters

We present a Reinforcement Learning Platform for Adversarial Black-box untargeted and targeted attacks, RLAB, that allows users to select from various distortion filters to create adversarial examples. The platform uses a Reinforcement Learning agent to add minimum distortion to input images while still causing misclassification by the target model. The agent uses a novel dual-action method to explore the input image at each step to identify sensitive regions for adding distortions while removing noises that have less impact on the target model. This dual action leads to faster and more efficient convergence of the attack. The platform can also be used to measure the robustness of image classification models against specific distortion types. Also, retraining the model with adversarial samples significantly improved robustness when evaluated on benchmark datasets. The proposed platform outperforms state-of-the-art methods in terms of the average number of queries required to cause misclassification. This advances trustworthiness with a positive social impact.

arXiv:2501.12311

Heuristic Deep Reinforcement Learning for Phase Shift Optimization in RIS-assisted Secure Satellite Communication Systems with RSMA

This paper presents a novel heuristic deep reinforcement learning (HDRL) framework designed to optimize reconfigurable intelligent surface (RIS) phase shifts in secure satellite communication systems utilizing rate splitting multiple access (RSMA). The proposed HDRL approach addresses the challenges of large action spaces inherent in deep reinforcement learning by integrating heuristic algorithms, thus improving exploration efficiency and leading to faster convergence toward optimal solutions. We validate the effectiveness of HDRL through comprehensive simulations, demonstrating its superiority over traditional algorithms, including random phase shift, greedy algorithm, exhaustive search, and Deep Q-Network (DQN), in terms of secure sum rate and computational efficiency. Additionally, we compare the performance of RSMA with non-orthogonal multiple access (NOMA), highlighting that RSMA, particularly when implemented with an increased number of RIS elements, significantly enhances secure communication performance. The results indicate that HDRL is a powerful tool for improving the security and reliability of RSMA satellite communication systems, offering a practical balance between performance and computational demands.

arXiv:2501.12362

ARM-IRL: Adaptive Resilience Metric Quantification Using Inverse Reinforcement Learning

Resilience of safety-critical systems is gaining importance, particularly with the increasing number of cyber and physical threats. Cyber-physical threats are becoming increasingly prevalent, as digital systems are ubiquitous in critical infrastructure. The challenge with determining the resilience of cyber-physical systems is identifying a set of resilience metrics that can adapt to the changing states of the system. A static resilience metric can lead to an inaccurate estimation of system state, and can result in unintended consequences against cyber threats. In this work, we propose a data-driven method for adaptive resilience metric learning. The primary goal is to learn a single resilience metric by formulating an inverse reinforcement learning problem that learns a reward or objective from a set of control actions from an expert. It learns the structure or parameters of the reward function based on information provided by expert demonstrations. Most prior work has considered static weights or theories from fuzzy logic to formulate a single resilience metric. Instead, this work learns the resilience metric, represented as reward function, using adversarial inverse reinforcement learning, to determine the optimal policy through training the generator discriminator in parallel. We evaluate our proposed technique in scenarios such as optimal communication network rerouting, power distribution network reconfiguration, and a combined cyber-physical restoration of critical load using the IEEE 123-bus system.

arXiv:2501.13883공식 코드 · Papers with Code

Utilizing Evolution Strategies to Train Transformers in Reinforcement Learning

We explore a capability of evolution strategies to train an agent with its policy based on a transformer architecture in a reinforcement learning setting. We performed experiments using OpenAI's highly parallelizable evolution strategy to train Decision Transformer in Humanoid locomotion environment and in the environment of Atari games, testing the ability of this black-box optimization technique to train even such relatively large and complicated models (compared to those previously tested in the literature). We also proposed a method to aid the training by first pretraining the model before using the OpenAI-ES to train it further, and tested its effectiveness. The examined evolution strategy proved to be, in general, capable of achieving strong results and managed to obtain high-performing agents. Therefore, the pretraining was shown to be unnecessary; yet still, it helped us observe and formulate several further insights.

arXiv:2501.13592공식 코드 · Papers with Code

WFCRL: A Multi-Agent Reinforcement Learning Benchmark for Wind Farm Control

The wind farm control problem is challenging, since conventional model-based control strategies require tractable models of complex aerodynamical interactions between the turbines and suffer from the curse of dimension when the number of turbines increases. Recently, model-free and multi-agent reinforcement learning approaches have been used to address this challenge. In this article, we introduce WFCRL (Wind Farm Control with Reinforcement Learning), the first open suite of multi-agent reinforcement learning environments for the wind farm control problem. WFCRL frames a cooperative Multi-Agent Reinforcement Learning (MARL) problem: each turbine is an agent and can learn to adjust its yaw, pitch or torque to maximize the common objective (e.g. the total power production of the farm). WFCRL also offers turbine load observations that will allow to optimize the farm performance while limiting turbine structural damages. Interfaces with two state-of-the-art farm simulators are implemented in WFCRL: a static simulator (FLORIS) and a dynamic simulator (FAST.Farm). For each simulator, $10$ wind layouts are provided, including $5$ real wind farms. Two state-of-the-art online MARL algorithms are implemented to illustrate the scaling challenges. As learning online on FAST.Farm is highly time-consuming, WFCRL offers the possibility of designing transfer learning strategies from FLORIS to FAST.Farm.

arXiv:2501.13264

RAG-Reward: Optimizing RAG with Reward Modeling and RLHF

Retrieval-augmented generation (RAG) enhances Large Language Models (LLMs) with relevant and up-to-date knowledge, improving their ability to answer knowledge-intensive questions. It has been shown to enhance both generation quality and trustworthiness. While numerous works have focused on improving retrieval, generation, and evaluation, the role of reward models in reinforcement learning for optimizing RAG and establishing automated benchmarking pipelines remains underexplored. In this paper, we introduce \textbf{RAG-Reward}, a dataset designed to enable \textit{hallucination-free, comprehensive, reliable, and efficient RAG}. We define four key metrics for assessing generation quality and develop an automated annotation pipeline that leverages multiple LLMs to generate outputs across diverse RAG scenarios. GPT-4o is used to evaluate and construct preference data. Using \textbf{RAG-Reward}, we train reward models and apply reinforcement learning with human feedback (RLHF) to improve LLMs' effectiveness in RAG. Experimental results show that our reward model achieves state-of-the-art performance on a held-out test set, demonstrating both the effectiveness of our approach and the quality of our dataset. Furthermore, the improved generation quality of the trained policy model highlights the feasibility of using RLHF to enhance RAG pipelines.

arXiv:2501.13252

Exploring the Technology Landscape through Topic Modeling, Expert Involvement, and Reinforcement Learning

In today's rapidly evolving technological landscape, organizations face the challenge of integrating external insights into their decision-making processes to stay competitive. To address this issue, this study proposes a method that combines topic modeling, expert knowledge inputs, and reinforcement learning (RL) to enhance the detection of technological changes. The method has four main steps: (1) Build a relevant topic model, starting with textual data like documents and reports to find key themes. (2) Create aspect-based topic models. Experts use curated keywords to build models that showcase key domain-specific aspects. (3) Iterative analysis and RL driven refinement: We examine metrics such as topic magnitude, similarity, entropy shifts, and how models change over time. We optimize topic selection with RL. Our reward function balances the diversity and similarity of the topics. (4) Synthesis and operational integration: Each iteration provides insights. In the final phase, the experts check these insights and reach new conclusions. These conclusions are designed for use in the firm's operational processes. The application is tested by forecasting trends in quantum communication. Results demonstrate the method's effectiveness in identifying, ranking, and tracking trends that align with expert input, providing a robust tool for exploring evolving technological landscapes. This research offers a scalable and adaptive solution for organizations to make informed strategic decisions in dynamic environments.

arXiv:2501.13333공식 코드 · Papers with Code

AgentRec: Agent Recommendation Using Sentence Embeddings Aligned to Human Feedback

Multi-agent systems must decide which agent is the most appropriate for a given task. We propose a novel architecture for recommending which LLM agent out of many should perform a task given a natural language prompt by extending the Sentence-BERT (SBERT) encoder model. On test data, we are able to achieve a top-1 accuracy of 92.2% with each classification taking less than 300 milliseconds. In contrast to traditional classification methods, our architecture is computationally cheap, adaptive to new classes, interpretable, and controllable with arbitrary metrics through reinforcement learning. By encoding natural language prompts into sentence embeddings, our model captures the semantic content relevant to recommending an agent. The distance between sentence embeddings that belong to the same agent is then minimized through fine-tuning and aligned to human values through reinforcement learning from human feedback. This allows the classification of natural language prompts based on their nearest neighbors by measuring the cosine similarity between embeddings. This work is made possible through the generation of a synthetic dataset for agent recommendation, which we have open-sourced to the public along with the code for AgentRec recommendation system at https://github.com/joshprk/agentrec.

arXiv:2501.13200공식 코드 · Papers with Code

SRMT: Shared Memory for Multi-agent Lifelong Pathfinding

Multi-agent reinforcement learning (MARL) demonstrates significant progress in solving cooperative and competitive multi-agent problems in various environments. One of the principal challenges in MARL is the need for explicit prediction of the agents' behavior to achieve cooperation. To resolve this issue, we propose the Shared Recurrent Memory Transformer (SRMT) which extends memory transformers to multi-agent settings by pooling and globally broadcasting individual working memories, enabling agents to exchange information implicitly and coordinate their actions. We evaluate SRMT on the Partially Observable Multi-Agent Pathfinding problem in a toy Bottleneck navigation task that requires agents to pass through a narrow corridor and on a POGEMA benchmark set of tasks. In the Bottleneck task, SRMT consistently outperforms a variety of reinforcement learning baselines, especially under sparse rewards, and generalizes effectively to longer corridors than those seen during training. On POGEMA maps, including Mazes, Random, and MovingAI, SRMT is competitive with recent MARL, hybrid, and planning-based algorithms. These results suggest that incorporating shared recurrent memory into the transformer-based architectures can enhance coordination in decentralized multi-agent systems. The source code for training and evaluation is available on GitHub: https://github.com/Aloriosa/srmt.