PyTorchKR Papers

최신 논문

총 1,873편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2407.08910

PAIL: Performance based Adversarial Imitation Learning Engine for Carbon Neutral Optimization

Achieving carbon neutrality within industrial operations has become increasingly imperative for sustainable development. It is both a significant challenge and a key opportunity for operational optimization in industry 4.0. In recent years, Deep Reinforcement Learning (DRL) based methods offer promising enhancements for sequential optimization processes and can be used for reducing carbon emissions. However, existing DRL methods need a pre-defined reward function to assess the impact of each action on the final sustainable development goals (SDG). In many real applications, such a reward function cannot be given in advance. To address the problem, this study proposes a Performance based Adversarial Imitation Learning (PAIL) engine. It is a novel method to acquire optimal operational policies for carbon neutrality without any pre-defined action rewards. Specifically, PAIL employs a Transformer-based policy generator to encode historical information and predict following actions within a multi-dimensional space. The entire action sequence will be iteratively updated by an environmental simulator. Then PAIL uses a discriminator to minimize the discrepancy between generated sequences and real-world samples of high SDG. In parallel, a Q-learning framework based performance estimator is designed to estimate the impact of each action on SDG. Based on these estimations, PAIL refines generated policies with the rewards from both discriminator and performance estimator. PAIL is evaluated on multiple real-world application cases and datasets. The experiment results demonstrate the effectiveness of PAIL comparing to other state-of-the-art baselines. In addition, PAIL offers meaningful interpretability for the optimization in carbon neutrality.

arXiv:2407.08803

PID Accelerated Temporal Difference Algorithms

Long-horizon tasks, which have a large discount factor, pose a challenge for most conventional reinforcement learning (RL) algorithms. Algorithms such as Value Iteration and Temporal Difference (TD) learning have a slow convergence rate and become inefficient in these tasks. When the transition distributions are given, PID VI was recently introduced to accelerate the convergence of Value Iteration using ideas from control theory. Inspired by this, we introduce PID TD Learning and PID Q-Learning algorithms for the RL setting, in which only samples from the environment are available. We give a theoretical analysis of the convergence of PID TD Learning and its acceleration compared to the conventional TD Learning. We also introduce a method for adapting PID gains in the presence of noise and empirically verify its effectiveness.

arXiv:2407.03982

Configuring Transmission Thresholds in IIoT Alarm Scenarios for Energy-Efficient Event Reporting

Industrial Internet of Things (IIoT) applications involve real-time monitoring, detection, and data analysis. This is challenged by the intermittent activity of IIoT devices (IIoTDs) and their limited battery capacity. Indeed, the former issue makes resource scheduling and random access difficult, while the latter constrains IIoTDs' lifetime and efficient operation. In this paper, we address interconnected aspects of these issues. Specifically, we focus on extending the battery life of IIoTDs sensing events/alarms by minimizing the number of unnecessary transmissions. Note that when multiple devices access the channel simultaneously, there are collisions, potentially leading to retransmissions, thus reducing energy efficiency. We propose a threshold-based transmission-decision policy based on the sensing quality and the network spatial deployment. We optimize the transmission thresholds using several approaches such as successive convex approximation, block coordinate descent methods, Voronoi diagrams, explainable machine learning, and algorithms based on natural selection and social behavior. Besides, we propose a new approach that reformulates the optimization problem as a $Q$-learning solution to promote adaptability to system dynamics. Through numerical evaluation, we demonstrate significant performance enhancements in complex IIoT environments, thus validating the practicality and effectiveness of the proposed solutions. We show that Q-learning performs the best, while the block coordinate descending method incurs the worst performance. Additionally, we compare the proposed methods with a benchmark assigning the same threshold to all the devices for transmission decision. Compared to the benchmark, up to 94\% and 60\% reduction in power consumption are achieved in low-density and high-density scenarios, respectively.

arXiv:2407.04811공식 코드 · Papers with Code

Simplifying Deep Temporal Difference Learning

Q-learning played a foundational role in the field reinforcement learning (RL). However, TD algorithms with off-policy data, such as Q-learning, or nonlinear function approximation like deep neural networks require several additional tricks to stabilise training, primarily a large replay buffer and target networks. Unfortunately, the delayed updating of frozen network parameters in the target network harms the sample efficiency and, similarly, the large replay buffer introduces memory and implementation overheads. In this paper, we investigate whether it is possible to accelerate and simplify off-policy TD training while maintaining its stability. Our key theoretical result demonstrates for the first time that regularisation techniques such as LayerNorm can yield provably convergent TD algorithms without the need for a target network or replay buffer, even with off-policy data. Empirically, we find that online, parallelised sampling enabled by vectorised environments stabilises training without the need for a large replay buffer. Motivated by these findings, we propose PQN, our simplified deep online Q-Learning algorithm. Surprisingly, this simple algorithm is competitive with more complex methods like: Rainbow in Atari, PPO-RNN in Craftax, QMix in Smax, and can be up to 50x faster than traditional DQN without sacrificing sample efficiency. In an era where PPO has become the go-to RL algorithm, PQN reestablishes off-policy Q-learning as a viable alternative.

arXiv:2407.06121

Periodic agent-state based Q-learning for POMDPs

The standard approach for Partially Observable Markov Decision Processes (POMDPs) is to convert them to a fully observed belief-state MDP. However, the belief state depends on the system model and is therefore not viable in reinforcement learning (RL) settings. A widely used alternative is to use an agent state, which is a model-free, recursively updateable function of the observation history. Examples include frame stacking and recurrent neural networks. Since the agent state is model-free, it is used to adapt standard RL algorithms to POMDPs. However, standard RL algorithms like Q-learning learn a stationary policy. Our main thesis that we illustrate via examples is that because the agent state does not satisfy the Markov property, non-stationary agent-state based policies can outperform stationary ones. To leverage this feature, we propose PASQL (periodic agent-state based Q-learning), which is a variant of agent-state-based Q-learning that learns periodic policies. By combining ideas from periodic Markov chains and stochastic approximation, we rigorously establish that PASQL converges to a cyclic limit and characterize the approximation error of the converged periodic policy. Finally, we present a numerical experiment to highlight the salient features of PASQL and demonstrate the benefit of learning periodic policies over stationary policies.

arXiv:2407.04521

Unified continuous-time q-learning for mean-field game and mean-field control problems

This paper studies the continuous-time q-learning in mean-field jump-diffusion models when the population distribution is not directly observable. We propose the integrated q-function in decoupled form (decoupled Iq-function) from the representative agent's perspective and establish its martingale characterization, which provides a unified policy evaluation rule for both mean-field game (MFG) and mean-field control (MFC) problems. Moreover, we consider the learning procedure where the representative agent updates the population distribution based on his own state values. Depending on the task to solve the MFG or MFC problem, we can employ the decoupled Iq-function differently to characterize the mean-field equilibrium policy or the mean-field optimal policy respectively. Based on these theoretical findings, we devise a unified q-learning algorithm for both MFG and MFC problems by utilizing test policies and the averaged martingale orthogonality condition. For several financial applications in the jump-diffusion setting, we obtain the exact parameterization of the decoupled Iq-functions and the value functions, and illustrate our q-learning algorithm with satisfactory performance.

arXiv:2407.04240공식 코드 · Papers with Code

A Multi-Step Minimax Q-learning Algorithm for Two-Player Zero-Sum Markov Games

An interesting iterative procedure is proposed to solve a two-player zero-sum Markov games. Under suitable assumption, the boundedness of the proposed iterates is obtained theoretically. Using results from stochastic approximation, the almost sure convergence of the proposed two-step minimax Q-learning is obtained theoretically. More specifically, the proposed algorithm converges to the game theoretic optimal value with probability one, when the model information is not known. Numerical simulation authenticate that the proposed algorithm is effective and easy to implement.

arXiv:2407.03888

Continuous-time q-Learning for Jump-Diffusion Models under Tsallis Entropy

This paper studies the continuous-time reinforcement learning in jump-diffusion models by featuring the q-learning (the continuous-time counterpart of Q-learning) under Tsallis entropy regularization. Contrary to the Shannon entropy, the general form of Tsallis entropy renders the optimal policy not necessary a Gibbs measure, where the Lagrange and KKT multipliers naturally arise from some constraints to ensure the learnt policy to be a probability density function. As a consequence, the characterization of the optimal policy using the q-function also involves a Lagrange multiplier. In response, we establish the martingale characterization of the q-function under Tsallis entropy and devise two q-learning algorithms depending on whether the Lagrange multiplier can be derived explicitly or not. In the latter case, we need to consider different parameterizations of the optimal q-function and the optimal policy and update them alternatively in an Actor-Critic manner. We also study two financial applications, namely, an optimal portfolio liquidation problem and a non-LQ control problem. It is interesting to see therein that the optimal policies under the Tsallis entropy regularization can be characterized explicitly, which are distributions concentrated on some compact support. The satisfactory performance of our q-learning algorithms is illustrated in each example.

arXiv:2407.03856공식 코드 · Papers with Code

Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation

Large Language Models (LLMs), trained on a large amount of corpus, have demonstrated remarkable abilities. However, it may not be sufficient to directly apply open-source LLMs like Llama to certain real-world scenarios, since most of them are trained for \emph{general} purposes. Thus, the demands for customizing publicly available LLMs emerge, but are currently under-studied. In this work, we consider customizing pre-trained LLMs with new human preferences. Specifically, the LLM should not only meet the new preference but also preserve its original capabilities after customization. Drawing inspiration from the observation that human preference can be expressed as a reward model, we propose to cast LLM customization as optimizing the sum of two reward functions, one of which (denoted as $r_1$) was used to pre-train the LLM while the other (denoted as $r_2$) characterizes the new human preference. The obstacle here is that both reward functions are unknown, making the application of modern reinforcement learning methods infeasible. Thanks to the residual Q-learning framework, we can restore the customized LLM with the pre-trained LLM and the \emph{residual Q-function} without the reward function $r_1$. Moreover, we find that for a fixed pre-trained LLM, the reward function $r_2$ can be derived from the residual Q-function, enabling us to directly learn the residual Q-function from the new human preference data upon the Bradley-Terry model. We name our method Q-Adapter as it introduces an adapter module to approximate the residual Q-function for customizing the pre-trained LLM towards the new preference. Experiments based on the Llama-3.1 model on the DSP dataset and HH-RLHF dataset illustrate the superior effectiveness of Q-Adapter on both retaining existing knowledge and learning new preferences. Code is available at \url{https://github.com/mansicer/Q-Adapter}.

arXiv:2407.04088

Artificial Intelligence and Algorithmic Price Collusion in Two-sided Markets

Algorithmic price collusion facilitated by artificial intelligence (AI) algorithms raises significant concerns. We examine how AI agents using Q-learning engage in tacit collusion in two-sided markets. Our experiments reveal that AI-driven platforms achieve higher collusion levels compared to Bertrand competition. Increased network externalities significantly enhance collusion, suggesting AI algorithms exploit them to maximize profits. Higher user heterogeneity or greater utility from outside options generally reduce collusion, while higher discount rates increase it. Tacit collusion remains feasible even at low discount rates. To mitigate collusive behavior and inform potential regulatory measures, we propose incorporating a penalty term in the Q-learning algorithm.

arXiv:2407.02369

Two-Step Q-Learning

Q-learning is a stochastic approximation version of the classic value iteration. The literature has established that Q-learning suffers from both maximization bias and slower convergence. Recently, multi-step algorithms have shown practical advantages over existing methods. This paper proposes a novel off-policy two-step Q-learning algorithms, without importance sampling. With suitable assumption it was shown that, iterates in the proposed two-step Q-learning is bounded and converges almost surely to the optimal Q-values. This study also address the convergence analysis of the smooth version of two-step Q-learning, i.e., by replacing max function with the log-sum-exp function. The proposed algorithms are robust and easy to implement. Finally, we test the proposed algorithms on benchmark problems such as the roulette problem, maximization bias problem, and randomly generated Markov decision processes and compare it with the existing methods available in literature. Numerical experiments demonstrate the superior performance of both the two-step Q-learning and its smooth variants.

arXiv:2407.01653

A Deep Reinforcement Learning Approach to Battery Management in Dairy Farming via Proximal Policy Optimization

Dairy farms consume a significant amount of electricity for their operations, and this research focuses on enhancing energy efficiency and minimizing the impact on the environment in the sector by maximizing the utilization of renewable energy sources. This research investigates the application of Proximal Policy Optimization (PPO), a deep reinforcement learning algorithm (DRL), to enhance dairy farming battery management. We evaluate the algorithm's effectiveness based on its ability to reduce reliance on the electricity grid, highlighting the potential of DRL to enhance energy management in dairy farming. Using real-world data our results demonstrate how the PPO approach outperforms Q-learning by 1.62% for reducing electricity import from the grid. This significant improvement highlights the potential of the Deep Reinforcement Learning algorithm for improving energy efficiency and sustainability in dairy farms.

arXiv:2407.00141

Towards Secure and Efficient Data Scheduling for Vehicular Social Networks

Efficient data transmission scheduling within vehicular environments poses a significant challenge due to the high mobility of such networks. Contemporary research predominantly centers on crafting cooperative scheduling algorithms tailored for vehicular networks. Notwithstanding, the intricacies of orchestrating scheduling in vehicular social networks both effectively and efficiently remain formidable. This paper introduces an innovative learning-based algorithm for scheduling data transmission that prioritizes efficiency and security within vehicular social networks. The algorithm first uses a specifically constructed neural network to enhance data processing capabilities. After this, it incorporates a Q-learning paradigm during the data transmission phase to optimize the information exchange, the privacy of which is safeguarded by differential privacy through the communication process. Comparative experiments demonstrate the superior performance of the proposed Q-learning enhanced scheduling algorithm relative to existing state-of-the-art scheduling algorithms in the context of vehicular social networks.

arXiv:2407.00699

Model-based Offline Reinforcement Learning with Lower Expectile Q-Learning

Model-based offline reinforcement learning (RL) is a compelling approach that addresses the challenge of learning from limited, static data by generating imaginary trajectories using learned models. However, these approaches often struggle with inaccurate value estimation from model rollouts. In this paper, we introduce a novel model-based offline RL method, Lower Expectile Q-learning (LEQ), which provides a low-bias model-based value estimation via lower expectile regression of $\lambda$-returns. Our empirical results show that LEQ significantly outperforms previous model-based offline RL methods on long-horizon tasks, such as the D4RL AntMaze tasks, matching or surpassing the performance of model-free approaches and sequence modeling approaches. Furthermore, LEQ matches the performance of state-of-the-art model-based and model-free methods in dense-reward environments across both state-based tasks (NeoRL and D4RL) and pixel-based tasks (V-D4RL), showing that LEQ works robustly across diverse domains. Our ablation studies demonstrate that lower expectile regression, $\lambda$-returns, and critic training on offline data are all crucial for LEQ.

arXiv:2407.02286공식 코드 · Papers with Code

Rethinking Data Augmentation for Robust LiDAR Semantic Segmentation in Adverse Weather

Existing LiDAR semantic segmentation methods often struggle with performance declines in adverse weather conditions. Previous work has addressed this issue by simulating adverse weather or employing universal data augmentation during training. However, these methods lack a detailed analysis and understanding of how adverse weather negatively affects LiDAR semantic segmentation performance. Motivated by this issue, we identified key factors of adverse weather and conducted a toy experiment to pinpoint the main causes of performance degradation: (1) Geometric perturbation due to refraction caused by fog or droplets in the air and (2) Point drop due to energy absorption and occlusions. Based on these findings, we propose new strategic data augmentation techniques. First, we introduced a Selective Jittering (SJ) that jitters points in the random range of depth (or angle) to mimic geometric perturbation. Additionally, we developed a Learnable Point Drop (LPD) to learn vulnerable erase patterns with a Deep Q-Learning Network to approximate the point drop phenomenon from adverse weather conditions. Without precise weather simulation, these techniques strengthen the LiDAR semantic segmentation model by exposing it to vulnerable conditions identified by our data-centric analysis. Experimental results confirmed the suitability of the proposed data augmentation methods for enhancing robustness against adverse weather conditions. Our method achieves a notable 39.5 mIoU on the SemanticKITTI-to-SemanticSTF benchmark, improving the baseline by 8.1\%p and establishing a new state-of-the-art. Our code will be released at \url{https://github.com/engineerJPark/LiDARWeather}.

arXiv:2406.19768공식 코드 · Papers with Code

Contextualized Hybrid Ensemble Q-learning: Learning Fast with Control Priors

Combining Reinforcement Learning (RL) with a prior controller can yield the best out of two worlds: RL can solve complex nonlinear problems, while the control prior ensures safer exploration and speeds up training. Prior work largely blends both components with a fixed weight, neglecting that the RL agent's performance varies with the training progress and across regions in the state space. Therefore, we advocate for an adaptive strategy that dynamically adjusts the weighting based on the RL agent's current capabilities. We propose a new adaptive hybrid RL algorithm, Contextualized Hybrid Ensemble Q-learning (CHEQ). CHEQ combines three key ingredients: (i) a time-invariant formulation of the adaptive hybrid RL problem treating the adaptive weight as a context variable, (ii) a weight adaption mechanism based on the parametric uncertainty of a critic ensemble, and (iii) ensemble-based acceleration for data-efficient RL. Evaluating CHEQ on a car racing task reveals substantially stronger data efficiency, exploration safety, and transferability to unknown scenarios than state-of-the-art adaptive hybrid RL methods.

arXiv:2406.18741

Decentralized Semantic Traffic Control in AVs Using RL and DQN for Dynamic Roadblocks

Autonomous Vehicles (AVs), furnished with sensors capable of capturing essential vehicle dynamics such as speed, acceleration, and precise location, possess the capacity to execute intelligent maneuvers, including lane changes, in anticipation of approaching roadblocks. Nevertheless, the sheer volume of sensory data and the processing necessary to derive informed decisions can often overwhelm the vehicles, rendering them unable to handle the task independently. Consequently, a common approach in traffic scenarios involves transmitting the data to servers for processing, a practice that introduces challenges, particularly in situations demanding real-time processing. In response to this challenge, we present a novel DL-based semantic traffic control system that entrusts semantic encoding responsibilities to the vehicles themselves. This system processes driving decisions obtained from a Reinforcement Learning (RL) agent, streamlining the decision-making process. Specifically, our framework envisions scenarios where abrupt roadblocks materialize due to factors such as road maintenance, accidents, or vehicle repairs, necessitating vehicles to make determinations concerning lane-keeping or lane-changing actions to navigate past these obstacles. To formulate this scenario mathematically, we employ a Markov Decision Process (MDP) and harness the Deep Q Learning (DQN) algorithm to unearth viable solutions.

arXiv:2406.18033공식 코드 · Papers with Code

Boosting Soft Q-Learning by Bounding

An agent's ability to leverage past experience is critical for efficiently solving new tasks. Prior work has focused on using value function estimates to obtain zero-shot approximations for solutions to a new task. In soft Q-learning, we show how any value function estimate can also be used to derive double-sided bounds on the optimal value function. The derived bounds lead to new approaches for boosting training performance which we validate experimentally. Notably, we find that the proposed framework suggests an alternative method for updating the Q-function, leading to boosted performance.

arXiv:2406.16258

MEReQ: Max-Ent Residual-Q Inverse RL for Sample-Efficient Alignment from Intervention

Aligning robot behavior with human preferences is crucial for deploying embodied AI agents in human-centered environments. A promising solution is interactive imitation learning from human intervention, where a human expert observes the policy's execution and provides interventions as feedback. However, existing methods often fail to utilize the prior policy efficiently to facilitate learning, thus hindering sample efficiency. In this work, we introduce MEReQ (Maximum-Entropy Residual-Q Inverse Reinforcement Learning), designed for sample-efficient alignment from human intervention. Instead of inferring the complete human behavior characteristics, MEReQ infers a residual reward function that captures the discrepancy between the human expert's and the prior policy's underlying reward functions. It then employs Residual Q-Learning (RQL) to align the policy with human preferences using this residual reward function. Extensive evaluations on simulated and real-world tasks demonstrate that MEReQ achieves sample-efficient policy alignment from human intervention.

arXiv:2406.14753

A General Control-Theoretic Approach for Reinforcement Learning: Theory and Algorithms

We devise a control-theoretic reinforcement learning approach to support direct learning of the optimal policy. We establish various theoretical properties of our approach, such as convergence and optimality of our analog of the Bellman operator and Q-learning, a new control-policy-variable gradient theorem, and a specific gradient ascent algorithm based on this theorem within the context of a specific control-theoretic framework. We empirically evaluate the performance of our control theoretic approach on several classical reinforcement learning tasks, demonstrating significant improvements in solution quality, sample complexity, and running time of our approach over state-of-the-art methods.