PyTorchKR Papers

최신 논문

총 13,741편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2401.15767공식 코드 · Papers with Code

LEACH-RLC: Enhancing IoT Data Transmission with Optimized Clustering and Reinforcement Learning

Wireless Sensor Networks (WSNs) play a pivotal role in enabling Internet of Things (IoT) devices with sensing and actuation capabilities. Operating in remote and resource-constrained environments, these IoT devices face challenges related to energy consumption, crucial for network longevity. Existing clustering protocols often suffer from high control overhead, inefficient cluster formation, and poor adaptability to dynamic network conditions, leading to suboptimal data transmission and reduced network lifetime. This paper introduces Low-Energy Adaptive Clustering Hierarchy with Reinforcement Learning-based Controller (LEACH-RLC), a novel clustering protocol designed to address these limitations by employing a Mixed Integer Linear Programming (MILP) approach for strategic selection of Cluster Heads (CHs) and node-to-cluster assignments. Additionally, it integrates a Reinforcement Learning (RL) agent to minimize control overhead by learning optimal timings for generating new clusters. LEACH-RLC aims to balance control overhead reduction without compromising overall network performance. Through extensive simulations, this paper investigates the frequency and opportune moments for generating new clustering solutions. Results demonstrate the superior performance of LEACH-RLC over state-of-the-art protocols, showcasing enhanced network lifetime, reduced average energy consumption, and minimized control overhead. The proposed protocol contributes to advancing the efficiency and adaptability of WSNs, addressing critical challenges in IoT deployments.

arXiv:2401.15449

Learning to Trust Your Feelings: Leveraging Self-awareness in LLMs for Hallucination Mitigation

We evaluate the ability of Large Language Models (LLMs) to discern and express their internal knowledge state, a key factor in countering factual hallucination and ensuring reliable application of LLMs. We observe a robust self-awareness of internal knowledge state in LLMs, evidenced by over 85% accuracy in knowledge probing. However, LLMs often fail to express their internal knowledge during generation, leading to factual hallucinations. We develop an automated hallucination annotation tool, Dreamcatcher, which merges knowledge probing and consistency checking methods to rank factual preference data. Using knowledge preference as reward, We propose a Reinforcement Learning from Knowledge Feedback (RLKF) training framework, leveraging reinforcement learning to enhance the factuality and honesty of LLMs. Our experiments across multiple models show that RLKF training effectively enhances the ability of models to utilize their internal knowledge state, boosting performance in a variety of knowledge-based and honesty-related tasks.

arXiv:2401.15273

Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learning

Federated reinforcement learning (FRL) has emerged as a promising paradigm for reducing the sample complexity of reinforcement learning tasks by exploiting information from different agents. However, when each agent interacts with a potentially different environment, little to nothing is known theoretically about the non-asymptotic performance of FRL algorithms. The lack of such results can be attributed to various technical challenges and their intricate interplay: Markovian sampling, linear function approximation, multiple local updates to save communication, heterogeneity in the reward functions and transition kernels of the agents' MDPs, and continuous state-action spaces. Moreover, in the on-policy setting, the behavior policies vary with time, further complicating the analysis. In response, we introduce FedSARSA, a novel federated on-policy reinforcement learning scheme, equipped with linear function approximation, to address these challenges and provide a comprehensive finite-time error analysis. Notably, we establish that FedSARSA converges to a policy that is near-optimal for all agents, with the extent of near-optimality proportional to the level of heterogeneity. Furthermore, we prove that FedSARSA leverages agent collaboration to enable linear speedups as the number of agents increases, which holds for both fixed and adaptive step-size configurations.

arXiv:2401.16013

SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning

In recent years, significant progress has been made in the field of robotic reinforcement learning (RL), enabling methods that handle complex image observations, train in the real world, and incorporate auxiliary data, such as demonstrations and prior experience. However, despite these advances, robotic RL remains hard to use. It is acknowledged among practitioners that the particular implementation details of these algorithms are often just as important (if not more so) for performance as the choice of algorithm. We posit that a significant challenge to widespread adoption of robotic RL, as well as further development of robotic RL methods, is the comparative inaccessibility of such methods. To address this challenge, we developed a carefully implemented library containing a sample efficient off-policy deep RL method, together with methods for computing rewards and resetting the environment, a high-quality controller for a widely-adopted robot, and a number of challenging example tasks. We provide this library as a resource for the community, describe its design choices, and present experimental results. Perhaps surprisingly, we find that our implementation can achieve very efficient learning, acquiring policies for PCB board assembly, cable routing, and object relocation between 25 to 50 minutes of training per policy on average, improving over state-of-the-art results reported for similar tasks in the literature. These policies achieve perfect or near-perfect success rates, extreme robustness even under perturbations, and exhibit emergent recovery and correction behaviors. We hope that these promising results and our high-quality open-source implementation will provide a tool for the robotics community to facilitate further developments in robotic RL. Our code, documentation, and videos can be found at https://serl-robot.github.io/

arXiv:2401.15480

Social Interpretable Reinforcement Learning

Reinforcement Learning (RL) bears the promise of being a game-changer in many applications. However, since most of the literature in the field is currently focused on opaque models, the use of RL in high-stakes scenarios, where interpretability is crucial, is still limited. Recently, some approaches to interpretable RL, e.g., based on Decision Trees, have been proposed, but one of the main limitations of these techniques is their training cost. To overcome this limitation, we propose a new method, called Social Interpretable RL (SIRL), that can substantially reduce the number of episodes needed for training. Our method mimics a social learning process, where each agent in a group learns to solve a given task based both on its own individual experience as well as the experience acquired together with its peers. Our approach is divided into the following two phases. (1) In the collaborative phase, all the agents in the population interact with a shared instance of the environment, where each agent observes the state and independently proposes an action. Then, voting is performed to choose the action that will actually be deployed in the environment. (2) In the individual phase, then, each agent refines its individual performance by interacting with its own instance of the environment. This mechanism makes the agents experience a larger number of episodes with little impact on the computational cost of the process. Our results (on 6 widely-known RL benchmarks) show that SIRL not only reduces the computational cost by a factor varying from a minimum of 43% to a maximum 76%, but it also increases the convergence speed and, often, improves the quality of the solutions.

arXiv:2401.15098

Hierarchical Continual Reinforcement Learning via Large Language Model

The ability to learn continuously in dynamic environments is a crucial requirement for reinforcement learning (RL) agents applying in the real world. Despite the progress in continual reinforcement learning (CRL), existing methods often suffer from insufficient knowledge transfer, particularly when the tasks are diverse. To address this challenge, we propose a new framework, Hierarchical Continual reinforcement learning via large language model (Hi-Core), designed to facilitate the transfer of high-level knowledge. Hi-Core orchestrates a twolayer structure: high-level policy formulation by a large language model (LLM), which represents agenerates a sequence of goals, and low-level policy learning that closely aligns with goal-oriented RL practices, producing the agent's actions in response to the goals set forth. The framework employs feedback to iteratively adjust and verify highlevel policies, storing them along with low-level policies within a skill library. When encountering a new task, Hi-Core retrieves relevant experience from this library to help to learning. Through experiments on Minigrid, Hi-Core has demonstrated its effectiveness in handling diverse CRL tasks, which outperforms popular baselines.

arXiv:2401.15059공식 코드 · Papers with Code

Fully Independent Communication in Multi-Agent Reinforcement Learning

Multi-Agent Reinforcement Learning (MARL) comprises a broad area of research within the field of multi-agent systems. Several recent works have focused specifically on the study of communication approaches in MARL. While multiple communication methods have been proposed, these might still be too complex and not easily transferable to more practical contexts. One of the reasons for that is due to the use of the famous parameter sharing trick. In this paper, we investigate how independent learners in MARL that do not share parameters can communicate. We demonstrate that this setting might incur into some problems, to which we propose a new learning scheme as a solution. Our results show that, despite the challenges, independent agents can still learn communication strategies following our method. Additionally, we use this method to investigate how communication in MARL is affected by different network capacities, both for sharing and not sharing parameters. We observe that communication may not always be needed and that the chosen agent network sizes need to be considered when used together with communication in order to achieve efficient learning.

arXiv:2401.14758공식 코드 · Papers with Code

Off-Policy Primal-Dual Safe Reinforcement Learning

Primal-dual safe RL methods commonly perform iterations between the primal update of the policy and the dual update of the Lagrange Multiplier. Such a training paradigm is highly susceptible to the error in cumulative cost estimation since this estimation serves as the key bond connecting the primal and dual update processes. We show that this problem causes significant underestimation of cost when using off-policy methods, leading to the failure to satisfy the safety constraint. To address this issue, we propose conservative policy optimization, which learns a policy in a constraint-satisfying area by considering the uncertainty in cost estimation. This improves constraint satisfaction but also potentially hinders reward maximization. We then introduce local policy convexification to help eliminate such suboptimality by gradually reducing the estimation uncertainty. We provide theoretical interpretations of the joint coupling effect of these two ingredients and further verify them by extensive experiments. Results on benchmark tasks show that our method not only achieves an asymptotic performance comparable to state-of-the-art on-policy methods while using much fewer samples, but also significantly reduces constraint violation during training. Our code is available at https://github.com/ZifanWu/CAL.

arXiv:2401.15043공식 코드 · Papers with Code

Health Text Simplification: An Annotated Corpus for Digestive Cancer Education and Novel Strategies for Reinforcement Learning

Objective: The reading level of health educational materials significantly influences the understandability and accessibility of the information, particularly for minoritized populations. Many patient educational resources surpass the reading level and complexity of widely accepted standards. There is a critical need for high-performing text simplification models in health information to enhance dissemination and literacy. This need is particularly acute in cancer education, where effective prevention and screening education can substantially reduce morbidity and mortality. Methods: We introduce Simplified Digestive Cancer (SimpleDC), a parallel corpus of cancer education materials tailored for health text simplification research, comprising educational content from the American Cancer Society, Centers for Disease Control and Prevention, and National Cancer Institute. Utilizing SimpleDC alongside the existing Med-EASi corpus, we explore Large Language Model (LLM)-based simplification methods, including fine-tuning, reinforcement learning (RL), reinforcement learning with human feedback (RLHF), domain adaptation, and prompt-based approaches. Our experimentation encompasses Llama 2 and GPT-4. A novel RLHF reward function is introduced, featuring a lightweight model adept at distinguishing between original and simplified texts, thereby enhancing the model's effectiveness with unlabeled data. Results: Fine-tuned Llama 2 models demonstrated high performance across various metrics. Our innovative RLHF reward function surpassed existing RL text simplification reward functions in effectiveness. The results underscore that RL/RLHF can augment fine-tuning, facilitating model training on unlabeled text and improving performance.

arXiv:2401.14488

Scilab-RL: A software framework for efficient reinforcement learning and cognitive modeling research

One problem with researching cognitive modeling and reinforcement learning (RL) is that researchers spend too much time on setting up an appropriate computational framework for their experiments. Many open source implementations of current RL algorithms exist, but there is a lack of a modular suite of tools combining different robotic simulators and platforms, data visualization, hyperparameter optimization, and baseline experiments. To address this problem, we present Scilab-RL, a software framework for efficient research in cognitive modeling and reinforcement learning for robotic agents. The framework focuses on goal-conditioned reinforcement learning using Stable Baselines 3 and the OpenAI gym interface. It enables native possibilities for experiment visualizations and hyperparameter optimization. We describe how these features enable researchers to conduct experiments with minimal time effort, thus maximizing research output.

arXiv:2306.09312공식 코드 · Papers with Code

Semantic HELM: A Human-Readable Memory for Reinforcement Learning

Reinforcement learning agents deployed in the real world often have to cope with partially observable environments. Therefore, most agents employ memory mechanisms to approximate the state of the environment. Recently, there have been impressive success stories in mastering partially observable environments, mostly in the realm of computer games like Dota 2, StarCraft II, or MineCraft. However, existing methods lack interpretability in the sense that it is not comprehensible for humans what the agent stores in its memory. In this regard, we propose a novel memory mechanism that represents past events in human language. Our method uses CLIP to associate visual inputs with language tokens. Then we feed these tokens to a pretrained language model that serves the agent as memory and provides it with a coherent and human-readable representation of the past. We train our memory mechanism on a set of partially observable environments and find that it excels on tasks that require a memory component, while mostly attaining performance on-par with strong baselines on tasks that do not. On a challenging continuous recognition task, where memorizing the past is crucial, our memory mechanism converges two orders of magnitude faster than prior methods. Since our memory mechanism is human-readable, we can peek at an agent's memory and check whether crucial pieces of information have been stored. This significantly enhances troubleshooting and paves the way toward more interpretable agents.

arXiv:2401.13947

Peer-to-Peer Energy Trading of Solar and Energy Storage: A Networked Multiagent Reinforcement Learning Approach

Utilizing distributed renewable and energy storage resources in local distribution networks via peer-to-peer (P2P) energy trading has long been touted as a solution to improve energy systems' resilience and sustainability. Consumers and prosumers (those who have energy generation resources), however, do not have the expertise to engage in repeated P2P trading, and the zero-marginal costs of renewables present challenges in determining fair market prices. To address these issues, we propose multi-agent reinforcement learning (MARL) frameworks to help automate consumers' bidding and management of their solar PV and energy storage resources, under a specific P2P clearing mechanism that utilizes the so-called supply-demand ratio. In addition, we show how the MARL frameworks can integrate physical network constraints to realize voltage control, hence ensuring physical feasibility of the P2P energy trading and paving way for real-world implementations.

arXiv:2401.13929공식 코드 · Papers with Code

HMM for Discovering Decision-Making Dynamics Using Reinforcement Learning Experiments

Major depressive disorder (MDD) presents challenges in diagnosis and treatment due to its complex and heterogeneous nature. Emerging evidence indicates that reward processing abnormalities may serve as a behavioral marker for MDD. To measure reward processing, patients perform computer-based behavioral tasks that involve making choices or responding to stimulants that are associated with different outcomes. Reinforcement learning (RL) models are fitted to extract parameters that measure various aspects of reward processing to characterize how patients make decisions in behavioral tasks. Recent findings suggest the inadequacy of characterizing reward learning solely based on a single RL model; instead, there may be a switching of decision-making processes between multiple strategies. An important scientific question is how the dynamics of learning strategies in decision-making affect the reward learning ability of individuals with MDD. Motivated by the probabilistic reward task (PRT) within the EMBARC study, we propose a novel RL-HMM framework for analyzing reward-based decision-making. Our model accommodates learning strategy switching between two distinct approaches under a hidden Markov model (HMM): subjects making decisions based on the RL model or opting for random choices. We account for continuous RL state space and allow time-varying transition probabilities in the HMM. We introduce a computationally efficient EM algorithm for parameter estimation and employ a nonparametric bootstrap for inference. We apply our approach to the EMBARC study to show that MDD patients are less engaged in RL compared to the healthy controls, and engagement is associated with brain activities in the negative affect circuitry during an emotional conflict task.

arXiv:2401.13014

A Novel Policy Iteration Algorithm for Nonlinear Continuous-Time H$\infty$ Control Problem

H{\infty} control of nonlinear continuous-time system depends on the solution of the Hamilton-Jacobi-Isaacs (HJI) equation, which has been proved impossible to obtain a closed-form solution due to the nonlinearity of HJI equation. In order to solve HJI equation, many iterative algorithms were proposed, and most of the algorithms were essentially Newton method when the fixed-point equation was constructed in a Banach space. Newton method is a local optimization method, it has small convergence region and needs the initial guess to be sufficiently close to the solution. Whereas damped Newton method enhances the robustness with respect to initial condition and has larger convergence region. In this paper, a novel reinforcement learning method which is named {\alpha}-policy iteration ({\alpha}-PI) is introduced for solving HJI equation. First, by constructing a damped Newton iteration operator equation, a generalized Bellman equation (GBE) is obtained. The GBE is an extension of bellman equation. And then, by iterating on the GBE, an on-policy {\alpha}-PI reinforcement learning method without using knowledge regarding to the system internal dynamics is proposed. Third, based on the on-policy {\alpha}-PI reinforcement learning method, we develop an off-policy {\alpha}-PI reinforcement learning method without requiring any knowledge of the system dynamics. Finally, the neural-network based adaptive critic implementation schemes of on-policy and off-policy {\alpha}-PI algorithms are derived respectively, and the batch least-squares method is used for calculating the weight parameters of neural networks. The effectiveness of the off-policy {\alpha}-PI algorithm is verified through computer simulation.

arXiv:2401.14226

Sample Efficient Reinforcement Learning by Automatically Learning to Compose Subtasks

Improving sample efficiency is central to Reinforcement Learning (RL), especially in environments where the rewards are sparse. Some recent approaches have proposed to specify reward functions as manually designed or learned reward structures whose integrations in the RL algorithms are claimed to significantly improve the learning efficiency. Manually designed reward structures can suffer from inaccuracy and existing automatically learning methods are often computationally intractable for complex tasks. The integration of inaccurate or partial reward structures in RL algorithms fail to learn optimal policies. In this work, we propose an RL algorithm that can automatically structure the reward function for sample efficiency, given a set of labels that signify subtasks. Given such minimal knowledge about the task, we train a high-level policy that selects optimal sub-tasks in each state together with a low-level policy that efficiently learns to complete each sub-task. We evaluate our algorithm in a variety of sparse-reward environments. The experiment results show that our approach significantly outperforms the state-of-art baselines as the difficulty of the task increases.

arXiv:2401.13246공식 코드 · Papers with Code

SEER: Facilitating Structured Reasoning and Explanation via Reinforcement Learning

Elucidating the reasoning process with structured explanations from question to answer is crucial, as it significantly enhances the interpretability, traceability, and trustworthiness of question-answering (QA) systems. However, structured explanations demand models to perform intricately structured reasoning, which poses great challenges. Most existing methods focus on single-step reasoning through supervised learning, ignoring logical dependencies between steps. Moreover, existing reinforcement learning (RL) based methods overlook the structured relationships, underutilizing the potential of RL in structured reasoning. In this paper, we propose SEER, a novel method that maximizes a structure-based return to facilitate structured reasoning and explanation. Our proposed structure-based return precisely describes the hierarchical and branching structure inherent in structured reasoning, effectively capturing the intricate relationships between different reasoning steps. In addition, we introduce a fine-grained reward function to meticulously delineate diverse reasoning steps. Extensive experiments show that SEER significantly outperforms state-of-the-art methods, achieving an absolute improvement of 6.9% over RL-based methods on EntailmentBank, a 4.4% average improvement on STREET benchmark, and exhibiting outstanding efficiency and cross-dataset generalization performance. Our code is available at https://github.com/Chen-GX/SEER.

arXiv:2401.13447

Symbolic Equation Solving via Reinforcement Learning

Machine-learning methods are gradually being adopted in a wide variety of social, economic, and scientific contexts, yet they are notorious for struggling with exact mathematics. A typical example is computer algebra, which includes tasks like simplifying mathematical terms, calculating formal derivatives, or finding exact solutions of algebraic equations. Traditional software packages for these purposes are commonly based on a huge database of rules for how a specific operation (e.g., differentiation) transforms a certain term (e.g., sine function) into another one (e.g., cosine function). These rules have usually needed to be discovered and subsequently programmed by humans. Efforts to automate this process by machine-learning approaches are faced with challenges like the singular nature of solutions to mathematical problems, when approximations are unacceptable, as well as hallucination effects leading to flawed reasoning. We propose a novel deep-learning interface involving a reinforcement-learning agent that operates a symbolic stack calculator to explore mathematical relations. By construction, this system is capable of exact transformations and immune to hallucination. Using the paradigmatic example of solving linear equations in symbolic form, we demonstrate how our reinforcement-learning agent autonomously discovers elementary transformation rules and step-by-step solutions.

arXiv:2401.12235

Stochastic Dynamic Power Dispatch with High Generalization and Few-Shot Adaption via Contextual Meta Graph Reinforcement Learning

Reinforcement learning is an emerging approaches to facilitate multi-stage sequential decision-making problems. This paper studies a real-time multi-stage stochastic power dispatch considering multivariate uncertainties. Current researches suffer from low generalization and practicality, that is, the learned dispatch policy can only handle a specific dispatch scenario, its performance degrades significantly if actual samples and training samples are inconsistent. To fill these gaps, a novel contextual meta graph reinforcement learning (Meta-GRL) for a highly generalized multi-stage optimal dispatch policy is proposed. Specifically, a more general contextual Markov decision process (MDP) and scalable graph representation are introduced to achieve a more generalized multi-stage stochastic power dispatch modeling. An upper meta-learner is proposed to encode context for different dispatch scenarios and learn how to achieve dispatch task identification while the lower policy learner learns context-specified dispatch policy. After sufficient offline learning, this approach can rapidly adapt to unseen and undefined scenarios with only a few updations of the hypothesis judgments generated by the meta-learner. Numerical comparisons with state-of-the-art policies and traditional reinforcement learning verify the optimality, efficiency, adaptability, and scalability of the proposed Meta-GRL.

arXiv:2401.12934

Reward-Relevance-Filtered Linear Offline Reinforcement Learning

This paper studies offline reinforcement learning with linear function approximation in a setting with decision-theoretic, but not estimation sparsity. The structural restrictions of the data-generating process presume that the transitions factor into a sparse component that affects the reward and could affect additional exogenous dynamics that do not affect the reward. Although the minimally sufficient adjustment set for estimation of full-state transition properties depends on the whole state, the optimal policy and therefore state-action value function depends only on the sparse component: we call this causal/decision-theoretic sparsity. We develop a method for reward-filtering the estimation of the state-action value function to the sparse component by a modification of thresholded lasso in least-squares policy evaluation. We provide theoretical guarantees for our reward-filtered linear fitted-Q-iteration, with sample complexity depending only on the size of the sparse component.

arXiv:2401.12882

Model-Free $δ$-Policy Iteration Based on Damped Newton Method for Nonlinear Continuous-Time H$\infty$ Tracking Control

This paper presents a {\delta}-PI algorithm which is based on damped Newton method for the H{\infty} tracking control problem of unknown continuous-time nonlinear system. A discounted performance function and an augmented system are used to get the tracking Hamilton-Jacobi-Isaac (HJI) equation. Tracking HJI equation is a nonlinear partial differential equation, traditional reinforcement learning methods for solving the tracking HJI equation are mostly based on the Newton method, which usually only satisfies local convergence and needs a good initial guess. Based upon the damped Newton iteration operator equation, a generalized tracking Bellman equation is derived firstly. The {\delta}-PI algorithm can seek the optimal solution of the tracking HJI equation by iteratively solving the generalized tracking Bellman equation. On-policy learning and off-policy learning {\delta}-PI reinforcement learning methods are provided, respectively. Off-policy version {\delta}-PI algorithm is a model-free algorithm which can be performed without making use of a priori knowledge of the system dynamics. NN-based implementation scheme for the off-policy {\delta}-PI algorithms is shown. The suitability of the model-free {\delta}-PI algorithm is illustrated with a nonlinear system simulation.