PyTorchKR Papers

최신 논문

총 1,872편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2310.19308공식 코드 · Papers with Code

Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning

Off-policy dynamic programming (DP) techniques such as $Q$-learning have proven to be important in sequential decision-making problems. In the presence of function approximation, however, these techniques often diverge due to the absence of Bellman completeness in the function classes considered, a crucial condition for the success of DP-based methods. In this paper, we show how off-policy learning techniques based on return-conditioned supervised learning (RCSL) are able to circumvent these challenges of Bellman completeness, converging under significantly more relaxed assumptions inherited from supervised learning. We prove there exists a natural environment in which if one uses two-layer multilayer perceptron as the function approximator, the layer width needs to grow linearly with the state space size to satisfy Bellman completeness while a constant layer width is enough for RCSL. These findings take a step towards explaining the superior empirical performance of RCSL methods compared to DP-based methods in environments with near-optimal datasets. Furthermore, in order to learn from sub-optimal datasets, we propose a simple framework called MBRCSL, granting RCSL methods the ability of dynamic programming to stitch together segments from distinct trajectories. MBRCSL leverages learned dynamics models and forward sampling to accomplish trajectory stitching while avoiding the need for Bellman completeness that plagues all dynamic programming algorithms. We propose both theoretical analysis and experimental evaluation to back these claims, outperforming state-of-the-art model-free and model-based offline RL algorithms across several simulated robotics problems.

arXiv:2310.18803

Weakly Coupled Deep Q-Networks

We propose weakly coupled deep Q-networks (WCDQN), a novel deep reinforcement learning algorithm that enhances performance in a class of structured problems called weakly coupled Markov decision processes (WCMDP). WCMDPs consist of multiple independent subproblems connected by an action space constraint, which is a structural property that frequently emerges in practice. Despite this appealing structure, WCMDPs quickly become intractable as the number of subproblems grows. WCDQN employs a single network to train multiple DQN "subagents", one for each subproblem, and then combine their solutions to establish an upper bound on the optimal action value. This guides the main DQN agent towards optimality. We show that the tabular version, weakly coupled Q-learning (WCQL), converges almost surely to the optimal action value. Numerical experiments show faster convergence compared to DQN and related techniques in settings with as many as 10 subproblems, $3^{10}$ total actions, and a continuous state space.

arXiv:2310.18186

Model-free Posterior Sampling via Learning Rate Randomization

In this paper, we introduce Randomized Q-learning (RandQL), a novel randomized model-free algorithm for regret minimization in episodic Markov Decision Processes (MDPs). To the best of our knowledge, RandQL is the first tractable model-free posterior sampling-based algorithm. We analyze the performance of RandQL in both tabular and non-tabular metric space settings. In tabular MDPs, RandQL achieves a regret bound of order $\widetilde{\mathcal{O}}(\sqrt{H^{5}SAT})$, where $H$ is the planning horizon, $S$ is the number of states, $A$ is the number of actions, and $T$ is the number of episodes. For a metric state-action space, RandQL enjoys a regret bound of order $\widetilde{\mathcal{O}}(H^{5/2} T^{(d_z+1)/(d_z+2)})$, where $d_z$ denotes the zooming dimension. Notably, RandQL achieves optimistic exploration without using bonuses, relying instead on a novel idea of learning rate randomization. Our empirical study shows that RandQL outperforms existing approaches on baseline exploration environments.

arXiv:2310.17915

Lifting the Veil: Unlocking the Power of Depth in Q-learning

With the help of massive data and rich computational resources, deep Q-learning has been widely used in operations research and management science and has contributed to great success in numerous applications, including recommender systems, supply chains, games, and robotic manipulation. However, the success of deep Q-learning lacks solid theoretical verification and interpretability. The aim of this paper is to theoretically verify the power of depth in deep Q-learning. Within the framework of statistical learning theory, we rigorously prove that deep Q-learning outperforms its traditional version by demonstrating its good generalization error bound. Our results reveal that the main reason for the success of deep Q-learning is the excellent performance of deep neural networks (deep nets) in capturing the special properties of rewards namely, spatial sparseness and piecewise constancy, rather than their large capacities. In this paper, we make fundamental contributions to the field of reinforcement learning by answering to the following three questions: Why does deep Q-learning perform so well? When does deep Q-learning perform better than traditional Q-learning? How many samples are required to achieve a specific prediction accuracy for deep Q-learning? Our theoretical assertions are verified by applying deep Q-learning in the well-known beer game in supply chain management and a simulated recommender system.

arXiv:2310.16748

Integrated Freeway Traffic Control Using Q-Learning with Adjacent Arterial Traffic Considerations

Numerous studies have shown the effectiveness of intelligent transportation system techniques such as variable speed limit (VSL), lane change (LC) control, and ramp metering (RM) in freeway traffic flow control. The integration of these techniques has the potential to further enhance the traffic operation efficiency of both freeway and adjacent arterial networks. In this regard, we propose a freeway traffic control (FTC) strategy that coordinates VSL, LC, RM actions using a Q-learning (QL) framework which takes into account arterial traffic characteristics. The signal timing and demands of adjacent arterial intersections are incorporated as state variables of the FTC agent. The FTC agent is initially trained offline using a single-section road network, and subsequently deployed online in a connected freeway and arterial simulation network for continuous learning. The arterial network is assumed to be regulated by a traffic-responsive signal control strategy based on a cycle length model. Microscopic simulations demonstrate that the fully-trained FTC agent provides significant reductions in freeway travel time and the number of stops in scenarios with traffic congestion. It clearly outperforms an uncoordinated FTC and a decentralized feedback control strategy. Even though the FTC agent does not control the arterial traffic signals, it leads to shorter average queue lengths at arterial intersections by taking into account the arterial traffic conditions in controlling freeway traffic. These results motivate a future research where the QL framework will also include the control of arterial traffic signals.

arXiv:2310.16173

On the Convergence and Sample Complexity Analysis of Deep Q-Networks with $ε$-Greedy Exploration

This paper provides a theoretical understanding of Deep Q-Network (DQN) with the $\varepsilon$-greedy exploration in deep reinforcement learning. Despite the tremendous empirical achievement of the DQN, its theoretical characterization remains underexplored. First, the exploration strategy is either impractical or ignored in the existing analysis. Second, in contrast to conventional Q-learning algorithms, the DQN employs the target network and experience replay to acquire an unbiased estimation of the mean-square Bellman error (MSBE) utilized in training the Q-network. However, the existing theoretical analysis of DQNs lacks convergence analysis or bypasses the technical challenges by deploying a significantly overparameterized neural network, which is not computationally efficient. This paper provides the first theoretical convergence and sample complexity analysis of the practical setting of DQNs with $\epsilon$-greedy policy. We prove an iterative procedure with decaying $\epsilon$ converges to the optimal Q-value function geometrically. Moreover, a higher level of $\epsilon$ values enlarges the region of convergence but slows down the convergence, while the opposite holds for a lower level of $\epsilon$ values. Experiments justify our established theoretical insights on DQNs.

arXiv:2310.14938

AI on the Water: Applying DRL to Autonomous Vessel Navigation

Human decision-making errors cause a majority of globally reported marine accidents. As a result, automation in the marine industry has been gaining more attention in recent years. Obstacle avoidance becomes very challenging for an autonomous surface vehicle in an unknown environment. We explore the feasibility of using Deep Q-Learning (DQN), a deep reinforcement learning approach, for controlling an underactuated autonomous surface vehicle to follow a known path while avoiding collisions with static and dynamic obstacles. The ship's motion is described using a three-degree-of-freedom (3-DOF) dynamic model. The KRISO container ship (KCS) is chosen for this study because it is a benchmark hull used in several studies, and its hydrodynamic coefficients are readily available for numerical modelling. This study shows that Deep Reinforcement Learning (DRL) can achieve path following and collision avoidance successfully and can be a potential candidate that may be investigated further to achieve human-level or even better decision-making for autonomous marine vehicles.

arXiv:2310.13129공식 코드 · Papers with Code

Deep Reinforcement Learning-based Intelligent Traffic Signal Controls with Optimized CO2 emissions

Nowadays, transportation networks face the challenge of sub-optimal control policies that can have adverse effects on human health, the environment, and contribute to traffic congestion. Increased levels of air pollution and extended commute times caused by traffic bottlenecks make intersection traffic signal controllers a crucial component of modern transportation infrastructure. Despite several adaptive traffic signal controllers in literature, limited research has been conducted on their comparative performance. Furthermore, despite carbon dioxide (CO2) emissions' significance as a global issue, the literature has paid limited attention to this area. In this report, we propose EcoLight, a reward shaping scheme for reinforcement learning algorithms that not only reduces CO2 emissions but also achieves competitive results in metrics such as travel time. We compare the performance of tabular Q-Learning, DQN, SARSA, and A2C algorithms using metrics such as travel time, CO2 emissions, waiting time, and stopped time. Our evaluation considers multiple scenarios that encompass a range of road users (trucks, buses, cars) with varying pollution levels.

arXiv:2310.12955공식 코드 · Papers with Code

Towards Robust Offline Reinforcement Learning under Diverse Data Corruption

Offline reinforcement learning (RL) presents a promising approach for learning reinforced policies from offline datasets without the need for costly or unsafe interactions with the environment. However, datasets collected by humans in real-world environments are often noisy and may even be maliciously corrupted, which can significantly degrade the performance of offline RL. In this work, we first investigate the performance of current offline RL algorithms under comprehensive data corruption, including states, actions, rewards, and dynamics. Our extensive experiments reveal that implicit Q-learning (IQL) demonstrates remarkable resilience to data corruption among various offline RL algorithms. Furthermore, we conduct both empirical and theoretical analyses to understand IQL's robust performance, identifying its supervised policy learning scheme as the key factor. Despite its relative robustness, IQL still suffers from heavy-tail targets of Q functions under dynamics corruption. To tackle this challenge, we draw inspiration from robust statistics to employ the Huber loss to handle the heavy-tailedness and utilize quantile estimators to balance penalization for corrupted data and learning stability. By incorporating these simple yet effective modifications into IQL, we propose a more robust offline RL approach named Robust IQL (RIQL). Extensive experiments demonstrate that RIQL exhibits highly robust performance when subjected to diverse data corruption scenarios.

arXiv:2310.09358

Bad Values but Good Behavior: Learning Highly Misspecified Bandits and MDPs

Parametric, feature-based reward models are employed by a variety of algorithms in decision-making settings such as bandits and Markov decision processes (MDPs). The typical assumption under which the algorithms are analysed is realizability, i.e., that the true values of actions are perfectly explained by some parametric model in the class. We are, however, interested in the situation where the true values are (significantly) misspecified with respect to the model class. For parameterized bandits, contextual bandits and MDPs, we identify structural conditions, depending on the problem instance and model class, under which basic algorithms such as $\epsilon$-greedy, LinUCB and fitted Q-learning provably learn optimal policies under even highly misspecified models. This is in contrast to existing worst-case results for, say misspecified bandits, which show regret bounds that scale linearly with time, and shows that there can be a nontrivially large set of bandit instances that are robust to misspecification.

arXiv:2310.09299

Digital Twin Assisted Deep Reinforcement Learning for Online Admission Control in Sliced Network

The proliferation of diverse wireless services in 5G and beyond has led to the emergence of network slicing technologies. Among these, admission control plays a crucial role in achieving service-oriented optimization goals through the selective acceptance of service requests. Although deep reinforcement learning (DRL) forms the foundation in many admission control approaches thanks to its effectiveness and flexibility, initial instability with excessive convergence delay of DRL models hinders their deployment in real-world networks. We propose a digital twin (DT) accelerated DRL solution to address this issue. Specifically, we first formulate the admission decision-making process as a semi-Markov decision process, which is subsequently simplified into an equivalent discrete-time Markov decision process to facilitate the implementation of DRL methods. A neural network-based DT is established with a customized output layer for queuing systems, trained through supervised learning, and then employed to assist the training phase of the DRL model. Extensive simulations show that the DT-accelerated DRL improves resource utilization by over 40% compared to the directly trained state-of-the-art dueling deep Q-learning model. This improvement is achieved while preserving the model's capability to optimize the long-term rewards of the admission process.

arXiv:2310.08660공식 코드 · Papers with Code

Learning RL-Policies for Joint Beamforming Without Exploration: A Batch Constrained Off-Policy Approach

In this work, we consider the problem of network parameter optimization for rate maximization. We frame this as a joint optimization problem of power control, beam forming, and interference cancellation. We consider the setting where multiple Base Stations (BSs) communicate with multiple user equipment (UEs). Because of the exponential computational complexity of brute force search, we instead solve this nonconvex optimization problem using deep reinforcement learning (RL) techniques. Modern communication systems are notorious for their difficulty in exactly modeling their behavior. This limits us in using RL-based algorithms as interaction with the environment is needed for the agent to explore and learn efficiently. Further, it is ill-advised to deploy the algorithm in the real world for exploration and learning because of the high cost of failure. In contrast to the previous RL-based solutions proposed, such as deep-Q network (DQN) based control, we suggest an offline model-based approach. We specifically consider discrete batch-constrained deep Q-learning (BCQ) and show that performance similar to DQN can be achieved with only a fraction of the data without exploring. This maximizes sample efficiency and minimizes risk in deploying a new algorithm to commercial networks. We provide the entire project resource, including code and data, at the following link: https://github.com/Heasung-Kim/ safe-rl-deployment-for-5g.

arXiv:2310.07292

Integrated Sensing and Communication Neighbor Discovery for MANET with Gossip Mechanism

Mobile Ad hoc Network (MANET), supporting Machine-Type Communication(MTC), has a strong demand for rapid networking. Neighbor Discovery (ND) is a key initial step in configuring MANETs and faces a serious challenge in decreasing convergence time. Integrated Sensing and Communication (ISAC), as one of the potential key technologies in the 6th Generation (6G) mobile networks, can obtain the sensing data as the priori information to accelerate ND convergence. In order to further reduce the convergence time of ND, this paper introduces the ISAC-enabled gossip mechanism into the ND algorithm. The prior information acquired by ISAC reduces the information redundancy brought by the gossip mechanism and thus decreases the probability of collision, which further improves convergence speed. The average number of discovered nodes within a given period is derived, which is applied as the critical metric to evaluate the performance of ND algorithms. The simulation results confirm the correctness of the theoretical derivation and show that the interplay between the prior mechanisms and the gossip mechanism significantly reduces the convergence time. In addition, to solve the problem of imperfect sensing information, reinforcement learning is applied. Under the constraints of the convergence condition, the non-Reply and non-Stop Algorithm based on Gossip and Q-learning (GQ-nRnS) proposed in this paper not only ensures the completeness of ND, but also maintains a high convergence speed of ND. Compared with the Q-learning-based ND algorithm (Q-ND), the average convergence time of the GQ-nRnS algorithm is reduced by about 66.4%.

arXiv:2310.06801

Inverse Factorized Q-Learning for Cooperative Multi-agent Imitation Learning

This paper concerns imitation learning (IL) (i.e, the problem of learning to mimic expert behaviors from demonstrations) in cooperative multi-agent systems. The learning problem under consideration poses several challenges, characterized by high-dimensional state and action spaces and intricate inter-agent dependencies. In a single-agent setting, IL has proven to be done efficiently through an inverse soft-Q learning process given expert demonstrations. However, extending this framework to a multi-agent context introduces the need to simultaneously learn both local value functions to capture local observations and individual actions, and a joint value function for exploiting centralized learning. In this work, we introduce a novel multi-agent IL algorithm designed to address these challenges. Our approach enables the centralized learning by leveraging mixing networks to aggregate decentralized Q functions. A main advantage of this approach is that the weights of the mixing networks can be trained using information derived from global states. We further establish conditions for the mixing networks under which the multi-agent objective function exhibits convexity within the Q function space. We present extensive experiments conducted on some challenging competitive and cooperative multi-agent game environments, including an advanced version of the Star-Craft multi-agent challenge (i.e., SMACv2), which demonstrates the effectiveness of our proposed algorithm compared to existing state-of-the-art multi-agent IL algorithms.

arXiv:2310.06343공식 코드 · Papers with Code

Boosting Continuous Control with Consistency Policy

Due to its training stability and strong expression, the diffusion model has attracted considerable attention in offline reinforcement learning. However, several challenges have also come with it: 1) The demand for a large number of diffusion steps makes the diffusion-model-based methods time inefficient and limits their applications in real-time control; 2) How to achieve policy improvement with accurate guidance for diffusion model-based policy is still an open problem. Inspired by the consistency model, we propose a novel time-efficiency method named Consistency Policy with Q-Learning (CPQL), which derives action from noise by a single step. By establishing a mapping from the reverse diffusion trajectories to the desired policy, we simultaneously address the issues of time efficiency and inaccurate guidance when updating diffusion model-based policy with the learned Q-function. We demonstrate that CPQL can achieve policy improvement with accurate guidance for offline reinforcement learning, and can be seamlessly extended for online RL tasks. Experimental results indicate that CPQL achieves new state-of-the-art performance on 11 offline and 21 online tasks, significantly improving inference speed by nearly 45 times compared to Diffusion-QL. We will release our code later.

arXiv:2310.06286

Suppressing Overestimation in Q-Learning through Adversarial Behaviors

The goal of this paper is to propose a new Q-learning algorithm with a dummy adversarial player, which is called dummy adversarial Q-learning (DAQ), that can effectively regulate the overestimation bias in standard Q-learning. With the dummy player, the learning can be formulated as a two-player zero-sum game. The proposed DAQ unifies several Q-learning variations to control overestimation biases, such as maxmin Q-learning and minmax Q-learning (proposed in this paper) in a single framework. The proposed DAQ is a simple but effective way to suppress the overestimation bias thourgh dummy adversarial behaviors and can be easily applied to off-the-shelf reinforcement learning algorithms to improve the performances. A finite-time convergence of DAQ is analyzed from an integrated perspective by adapting an adversarial Q-learning. The performance of the suggested DAQ is empirically demonstrated under various benchmark environments.

arXiv:2310.04930

Diff-Transfer: Model-based Robotic Manipulation Skill Transfer via Differentiable Physics Simulation

The capability to transfer mastered skills to accomplish a range of similar yet novel tasks is crucial for intelligent robots. In this work, we introduce $\textit{Diff-Transfer}$, a novel framework leveraging differentiable physics simulation to efficiently transfer robotic skills. Specifically, $\textit{Diff-Transfer}$ discovers a feasible path within the task space that brings the source task to the target task. At each pair of adjacent points along this task path, which is two sub-tasks, $\textit{Diff-Transfer}$ adapts known actions from one sub-task to tackle the other sub-task successfully. The adaptation is guided by the gradient information from differentiable physics simulations. We propose a novel path-planning method to generate sub-tasks, leveraging $Q$-learning with a task-level state and reward. We implement our framework in simulation experiments and execute four challenging transfer tasks on robotic manipulation, demonstrating the efficacy of $\textit{Diff-Transfer}$ through comprehensive experiments. Supplementary and Videos are on the website https://sites.google.com/view/difftransfer

arXiv:2310.05170공식 코드 · Papers with Code

DeepQTest: Testing Autonomous Driving Systems with Reinforcement Learning and Real-world Weather Data

Autonomous driving systems (ADSs) are capable of sensing the environment and making driving decisions autonomously. These systems are safety-critical, and testing them is one of the important approaches to ensure their safety. However, due to the inherent complexity of ADSs and the high dimensionality of their operating environment, the number of possible test scenarios for ADSs is infinite. Besides, the operating environment of ADSs is dynamic, continuously evolving, and full of uncertainties, which requires a testing approach adaptive to the environment. In addition, existing ADS testing techniques have limited effectiveness in ensuring the realism of test scenarios, especially the realism of weather conditions and their changes over time. Recently, reinforcement learning (RL) has demonstrated great potential in addressing challenging problems, especially those requiring constant adaptations to dynamic environments. To this end, we present DeepQTest, a novel ADS testing approach that uses RL to learn environment configurations with a high chance of revealing abnormal ADS behaviors. Specifically, DeepQTest employs Deep Q-Learning and adopts three safety and comfort measures to construct the reward functions. To ensure the realism of generated scenarios, DeepQTest defines a set of realistic constraints and introduces real-world weather conditions into the simulated environment. We employed three comparison baselines, i.e., random, greedy, and a state-of-the-art RL-based approach DeepCOllision, for evaluating DeepQTest on an industrial-scale ADS. Evaluation results show that DeepQTest demonstrated significantly better effectiveness in terms of generating scenarios leading to collisions and ensuring scenario realism compared with the baselines. In addition, among the three reward functions implemented in DeepQTest, Time-To-Collision is recommended as the best design according to our study.

arXiv:2310.05871

Dynamic value alignment through preference aggregation of multiple objectives

The development of ethical AI systems is currently geared toward setting objective functions that align with human objectives. However, finding such functions remains a research challenge, while in RL, setting rewards by hand is a fairly standard approach. We present a methodology for dynamic value alignment, where the values that are to be aligned with are dynamically changing, using a multiple-objective approach. We apply this approach to extend Deep $Q$-Learning to accommodate multiple objectives and evaluate this method on a simplified two-leg intersection controlled by a switching agent.Our approach dynamically accommodates the preferences of drivers on the system and achieves better overall performance across three metrics (speeds, stops, and waits) while integrating objectives that have competing or conflicting actions.

arXiv:2310.03814

Optimal Control of District Cooling Energy Plant with Reinforcement Learning and MPC

We consider the problem of optimal control of district cooling energy plants (DCEPs) consisting of multiple chillers, a cooling tower, and a thermal energy storage (TES), in the presence of time-varying electricity price. A straightforward application of model predictive control (MPC) requires solving a challenging mixed-integer nonlinear program (MINLP) because of the on/off of chillers and the complexity of the DCEP model. Reinforcement learning (RL) is an attractive alternative since its real-time control computation is much simpler. But designing an RL controller is challenging due to myriad design choices and computationally intensive training. In this paper, we propose an RL controller and an MPC controller for minimizing the electricity cost of a DCEP, and compare them via simulations. The two controllers are designed to be comparable in terms of objective and information requirements. The RL controller uses a novel Q-learning algorithm that is based on least-squares policy iteration. We describe the design choices for the RL controller, including the choice of state space and basis functions, that are found to be effective. The proposed MPC controller does not need a mixed integer solver for implementation, but only a nonlinear program (NLP) solver. A rule-based baseline controller is also proposed to aid in comparison. Simulation results show that the proposed RL and MPC controllers achieve similar savings over the baseline controller, about 17%.