PyTorchKR Papers

최신 논문

총 1,872편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2309.03202

Evaluation of Reinforcement Learning Techniques for Trading on a Diverse Portfolio

This work seeks to answer key research questions regarding the viability of reinforcement learning over the S&P 500 index. The on-policy techniques of Value Iteration (VI) and State-action-reward-state-action (SARSA) are implemented along with the off-policy technique of Q-Learning. The models are trained and tested on a dataset comprising multiple years of stock market data from 2000-2023. The analysis presents the results and findings from training and testing the models using two different time periods: one including the COVID-19 pandemic years and one excluding them. The results indicate that including market data from the COVID-19 period in the training dataset leads to superior performance compared to the baseline strategies. During testing, the on-policy approaches (VI and SARSA) outperform Q-learning, highlighting the influence of bias-variance tradeoff and the generalization capabilities of simpler policies. However, it is noted that the performance of Q-learning may vary depending on the stability of future market conditions. Future work is suggested, including experiments with updated Q-learning policies during testing and trading diverse individual stocks. Additionally, the exploration of alternative economic indicators for training the models is proposed.

arXiv:2309.05105

Convex Q Learning in a Stochastic Environment: Extended Version

The paper introduces the first formulation of convex Q-learning for Markov decision processes with function approximation. The algorithms and theory rest on a relaxation of a dual of Manne's celebrated linear programming characterization of optimal control. The main contributions firstly concern properties of the relaxation, described as a deterministic convex program: we identify conditions for a bounded solution, and a significant relationship between the solution to the new convex program, and the solution to standard Q-learning. The second set of contributions concern algorithm design and analysis: (i) A direct model-free method for approximating the convex program for Q-learning shares properties with its ideal. In particular, a bounded solution is ensured subject to a simple property of the basis functions; (ii) The proposed algorithms are convergent and new techniques are introduced to obtain the rate of convergence in a mean-square sense; (iii) The approach can be generalized to a range of performance criteria, and it is found that variance can be reduced by considering ``relative'' dynamic programming equations; (iv) The theory is illustrated with an application to a classical inventory control problem.

arXiv:2309.05391

Career Path Recommendations for Long-term Income Maximization: A Reinforcement Learning Approach

This study explores the potential of reinforcement learning algorithms to enhance career planning processes. Leveraging data from Randstad The Netherlands, the study simulates the Dutch job market and develops strategies to optimize employees' long-term income. By formulating career planning as a Markov Decision Process (MDP) and utilizing machine learning algorithms such as Sarsa, Q-Learning, and A2C, we learn optimal policies that recommend career paths with high-income occupations and industries. The results demonstrate significant improvements in employees' income trajectories, with RL models, particularly Q-Learning and Sarsa, achieving an average increase of 5% compared to observed career paths. The study acknowledges limitations, including narrow job filtering, simplifications in the environment formulation, and assumptions regarding employment continuity and zero application costs. Future research can explore additional objectives beyond income optimization and address these limitations to further enhance career planning processes.

arXiv:2309.00144

Multi Agent DeepRL based Joint Power and Subchannel Allocation in IAB networks

Integrated Access and Backhauling (IAB) is a viable approach for meeting the unprecedented need for higher data rates of future generations, acting as a cost-effective alternative to dense fiber-wired links. The design of such networks with constraints usually results in an optimization problem of non-convex and combinatorial nature. Under those situations, it is challenging to obtain an optimal strategy for the joint Subchannel Allocation and Power Allocation (SAPA) problem. In this paper, we develop a multi-agent Deep Reinforcement Learning (DeepRL) based framework for joint optimization of power and subchannel allocation in an IAB network to maximize the downlink data rate. SAPA using DDQN (Double Deep Q-Learning Network) can handle computationally expensive problems with huge action spaces associated with multiple users and nodes. Unlike the conventional methods such as game theory, fractional programming, and convex optimization, which in practice demand more and more accurate network information, the multi-agent DeepRL approach requires less environment network information. Simulation results show the proposed scheme's promising performance when compared with baseline (Deep Q-Learning Network and Random) schemes.

arXiv:2309.00017

Physics-Based Trajectory Design for Cellular-Connected UAV in Rainy Environments Based on Deep Reinforcement Learning

Cellular-connected unmanned aerial vehicles (UAVs) have gained increasing attention due to their potential to enhance conventional UAV capabilities by leveraging existing cellular infrastructure for reliable communications between UAVs and base stations. They have been used for various applications, including weather forecasting and search and rescue operations. However, under extreme weather conditions such as rainfall, it is challenging for the trajectory design of cellular UAVs, due to weak coverage regions in the sky, limitations of UAV flying time, and signal attenuation caused by raindrops. To this end, this paper proposes a physics-based trajectory design approach for cellular-connected UAVs in rainy environments. A physics-based electromagnetic simulator is utilized to take into account detailed environment information and the impact of rain on radio wave propagation. The trajectory optimization problem is formulated to jointly consider UAV flying time and signal-to-interference ratio, and is solved through a Markov decision process using deep reinforcement learning algorithms based on multi-step learning and double Q-learning. Optimal UAV trajectories are compared in examples with homogeneous atmosphere medium and rain medium. Additionally, a thorough study of varying weather conditions on trajectory design is provided, and the impact of weight coefficients in the problem formulation is discussed. The proposed approach has demonstrated great potential for UAV trajectory design under rainy weather conditions.

arXiv:2308.14946공식 코드 · Papers with Code

Reinforcement Learning for Sampling on Temporal Medical Imaging Sequences

Accelerated magnetic resonance imaging resorts to either Fourier-domain subsampling or better reconstruction algorithms to deal with fewer measurements while still generating medical images of high quality. Determining the optimal sampling strategy given a fixed reconstruction protocol often has combinatorial complexity. In this work, we apply double deep Q-learning and REINFORCE algorithms to learn the sampling strategy for dynamic image reconstruction. We consider the data in the format of time series, and the reconstruction method is a pre-trained autoencoder-typed neural network. We present a proof of concept that reinforcement learning algorithms are effective to discover the optimal sampling pattern which underlies the pre-trained reconstructor network (i.e., the dynamics in the environment). The code for replicating experiments can be found at https://github.com/zhishenhuang/RLsamp.

arXiv:2308.14652공식 코드 · Papers with Code

Learning Visual Tracking and Reaching with Deep Reinforcement Learning on a UR10e Robotic Arm

As technology progresses, industrial and scientific robots are increasingly being used in diverse settings. In many cases, however, programming the robot to perform such tasks is technically complex and costly. To maximize the utility of robots in industrial and scientific settings, they require the ability to quickly shift from one task to another. Reinforcement learning algorithms provide the potential to enable robots to learn optimal solutions to complete new tasks without directly reprogramming them. The current state-of-the-art in reinforcement learning, however, generally relies on fast simulations and parallelization to achieve optimal performance. These are often not possible in robotics applications. Thus, a significant amount of research is required to facilitate the efficient and safe, training and deployment of industrial and scientific reinforcement learning robots. This technical report outlines our initial research into the application of deep reinforcement learning on an industrial UR10e robot. The report describes the reinforcement learning environments created to facilitate policy learning with the UR10e, a robotic arm from Universal Robots, and presents our initial results in training deep Q-learning and proximal policy optimization agents on the developed reinforcement learning environments. Our results show that proximal policy optimization learns a better, more stable policy with less data than deep Q-learning. The corresponding code for this work is available at \url{https://github.com/cbellinger27/bendRL_reacher_tracker}

arXiv:2308.14295공식 코드 · Papers with Code

Traffic Light Control with Reinforcement Learning

Traffic light control is important for reducing congestion in urban mobility systems. This paper proposes a real-time traffic light control method using deep Q learning. Our approach incorporates a reward function considering queue lengths, delays, travel time, and throughput. The model dynamically decides phase changes based on current traffic conditions. The training of the deep Q network involves an offline stage from pre-generated data with fixed schedules and an online stage using real-time traffic data. A deep Q network structure with a "phase gate" component is used to simplify the model's learning task under different phases. A "memory palace" mechanism is used to address sample imbalance during the training process. We validate our approach using both synthetic and real-world traffic flow data on a road intersecting in Hangzhou, China. Results demonstrate significant performance improvements of the proposed method in reducing vehicle waiting time (57.1% to 100%), queue lengths (40.9% to 100%), and total travel time (16.8% to 68.0%) compared to traditional fixed signal plans.

arXiv:2308.12843

Actuator Trajectory Planning for UAVs with Overhead Manipulator using Reinforcement Learning

In this paper, we investigate the operation of an aerial manipulator system, namely an Unmanned Aerial Vehicle (UAV) equipped with a controllable arm with two degrees of freedom to carry out actuation tasks on the fly. Our solution is based on employing a Q-learning method to control the trajectory of the tip of the arm, also called end-effector. More specifically, we develop a motion planning model based on Time To Collision (TTC), which enables a quadrotor UAV to navigate around obstacles while ensuring the manipulator's reachability. Additionally, we utilize a model-based Q-learning model to independently track and control the desired trajectory of the manipulator's end-effector, given an arbitrary baseline trajectory for the UAV platform. Such a combination enables a variety of actuation tasks such as high-altitude welding, structural monitoring and repair, battery replacement, gutter cleaning, skyscrapper cleaning, and power line maintenance in hard-to-reach and risky environments while retaining compatibility with flight control firmware. Our RL-based control mechanism results in a robust control strategy that can handle uncertainties in the motion of the UAV, offering promising performance. Specifically, our method achieves 92% accuracy in terms of average displacement error (i.e. the mean distance between the target and obtained trajectory points) using Q-learning with 15,000 episodes

arXiv:2308.10284공식 코드 · Papers with Code

Towards Few-shot Coordination: Revisiting Ad-hoc Teamplay Challenge In the Game of Hanabi

Cooperative Multi-agent Reinforcement Learning (MARL) algorithms with Zero-Shot Coordination (ZSC) have gained significant attention in recent years. ZSC refers to the ability of agents to coordinate zero-shot (without additional interaction experience) with independently trained agents. While ZSC is crucial for cooperative MARL agents, it might not be possible for complex tasks and changing environments. Agents also need to adapt and improve their performance with minimal interaction with other agents. In this work, we show empirically that state-of-the-art ZSC algorithms have poor performance when paired with agents trained with different learning methods, and they require millions of interaction samples to adapt to these new partners. To investigate this issue, we formally defined a framework based on a popular cooperative multi-agent game called Hanabi to evaluate the adaptability of MARL methods. In particular, we created a diverse set of pre-trained agents and defined a new metric called adaptation regret that measures the agent's ability to efficiently adapt and improve its coordination performance when paired with some held-out pool of partners on top of its ZSC performance. After evaluating several SOTA algorithms using our framework, our experiments reveal that naive Independent Q-Learning (IQL) agents in most cases adapt as quickly as the SOTA ZSC algorithm Off-Belief Learning (OBL). This finding raises an interesting research question: How to design MARL algorithms with high ZSC performance and capability of fast adaptation to unseen partners. As a first step, we studied the role of different hyper-parameters and design choices on the adaptability of current MARL algorithms. Our experiments show that two categories of hyper-parameters controlling the training data diversity and optimization process have a significant impact on the adaptability of Hanabi agents.

arXiv:2308.09023

Reinforcement Learning for Battery Management in Dairy Farming

Dairy farming is a particularly energy-intensive part of the agriculture sector. Effective battery management is essential for renewable integration within the agriculture sector. However, controlling battery charging/discharging is a difficult task due to electricity demand variability, stochasticity of renewable generation, and energy price fluctuations. Despite the potential benefits of applying Artificial Intelligence (AI) to renewable energy in the context of dairy farming, there has been limited research in this area. This research is a priority for Ireland as it strives to meet its governmental goals in energy and sustainability. This research paper utilizes Q-learning to learn an effective policy for charging and discharging a battery within a dairy farm setting. The results demonstrate that the developed policy significantly reduces electricity costs compared to the established baseline algorithm. These findings highlight the effectiveness of reinforcement learning for battery management within the dairy farming sector.

arXiv:2308.08858

Improving Sample Efficiency of Model-Free Algorithms for Zero-Sum Markov Games

The problem of two-player zero-sum Markov games has recently attracted increasing interests in theoretical studies of multi-agent reinforcement learning (RL). In particular, for finite-horizon episodic Markov decision processes (MDPs), it has been shown that model-based algorithms can find an $\epsilon$-optimal Nash Equilibrium (NE) with the sample complexity of $O(H^3SAB/\epsilon^2)$, which is optimal in the dependence of the horizon $H$ and the number of states $S$ (where $A$ and $B$ denote the number of actions of the two players, respectively). However, none of the existing model-free algorithms can achieve such an optimality. In this work, we propose a model-free stage-based Q-learning algorithm and show that it achieves the same sample complexity as the best model-based algorithm, and hence for the first time demonstrate that model-free algorithms can enjoy the same optimality in the $H$ dependence as model-based algorithms. The main improvement of the dependency on $H$ arises by leveraging the popular variance reduction technique based on the reference-advantage decomposition previously used only for single-agent RL. However, such a technique relies on a critical monotonicity property of the value function, which does not hold in Markov games due to the update of the policy via the coarse correlated equilibrium (CCE) oracle. Thus, to extend such a technique to Markov games, our algorithm features a key novel design of updating the reference value functions as the pair of optimistic and pessimistic value functions whose value difference is the smallest in the history in order to achieve the desired improvement in the sample efficiency.

arXiv:2308.07329공식 코드 · Papers with Code

Variations on the Reinforcement Learning performance of Blackjack

Blackjack or "21" is a popular card-based game of chance and skill. The objective of the game is to win by obtaining a hand total higher than the dealer's without exceeding 21. The ideal blackjack strategy will maximize financial return in the long run while avoiding gambler's ruin. The stochastic environment and inherent reward structure of blackjack presents an appealing problem to better understand reinforcement learning agents in the presence of environment variations. Here we consider a q-learning solution for optimal play and investigate the rate of learning convergence of the algorithm as a function of deck size. A blackjack simulator allowing for universal blackjack rules is also implemented to demonstrate the extent to which a card counter perfectly using the basic strategy and hi-lo system can bring the house to bankruptcy and how environment variations impact this outcome. The novelty of our work is to place this conceptual understanding of the impact of deck size in the context of learning agent convergence.

arXiv:2308.07541

On-demand Cold Start Frequency Reduction with Off-Policy Reinforcement Learning in Serverless Computing

Function-as-a-Service (FaaS) is a cloud computing paradigm offering an event-driven execution model to applications. It features serverless attributes by eliminating resource management responsibilities from developers, and offers transparent and on-demand scalability of applications. To provide seamless on-demand scalability, new function instances are prepared to serve the incoming workload in the absence or unavailability of function instances. However, FaaS platforms are known to suffer from cold starts, where this function provisioning process introduces a non-negligible delay in function response and reduces the end-user experience. Therefore, the presented work focuses on reducing the frequent, on-demand cold starts on the platform by using Reinforcement Learning(RL). The proposed approach uses model-free Q-learning that consider function metrics such as CPU utilization, existing function instances, and response failure rate, to proactively initialize functions, in advance, based on the expected demand. The proposed solution is implemented on Kubeless and evaluated using an open-source function invocation trace applied to a matrix multiplication function. The evaluation results demonstrate a favourable performance of the RL-based agent when compared to Kubeless' default policy and a function keep-alive policy by improving throughput by up to 8.81% and reducing computation load and resource wastage by up to 55% and 37%, respectively, that is a direct outcome of reduced cold starts.

arXiv:2308.05711

A Comparison of Classical and Deep Reinforcement Learning Methods for HVAC Control

Reinforcement learning (RL) is a promising approach for optimizing HVAC control. RL offers a framework for improving system performance, reducing energy consumption, and enhancing cost efficiency. We benchmark two popular classical and deep RL methods (Q-Learning and Deep-Q-Networks) across multiple HVAC environments and explore the practical consideration of model hyper-parameter selection and reward tuning. The findings provide insight for configuring RL agents in HVAC systems, promoting energy-efficient and cost-effective operation.

arXiv:2308.03316

Deep Q-Network for Stochastic Process Environments

Reinforcement learning is a powerful approach for training an optimal policy to solve complex problems in a given system. This project aims to demonstrate the application of reinforcement learning in stochastic process environments with missing information, using Flappy Bird and a newly developed stock trading environment as case studies. We evaluate various structures of Deep Q-learning networks and identify the most suitable variant for the stochastic process environment. Additionally, we discuss the current challenges and propose potential improvements for further work in environment-building and reinforcement learning techniques.

arXiv:2308.03239

Unsynchronized Decentralized Q-Learning: Two Timescale Analysis By Persistence

Non-stationarity is a fundamental challenge in multi-agent reinforcement learning (MARL), where agents update their behaviour as they learn. Many theoretical advances in MARL avoid the challenge of non-stationarity by coordinating the policy updates of agents in various ways, including synchronizing times at which agents are allowed to revise their policies. Synchronization enables analysis of many MARL algorithms via multi-timescale methods, but such synchronization is infeasible in many decentralized applications. In this paper, we study an unsynchronized variant of the decentralized Q-learning algorithm, a recent MARL algorithm for stochastic games. We provide sufficient conditions under which the unsynchronized algorithm drives play to equilibrium with high probability. Our solution utilizes constant learning rates in the Q-factor update, which we show to be critical for relaxing the synchronization assumptions of earlier work. Our analysis also applies to unsynchronized generalizations of a number of other algorithms from the regret testing tradition, whose performance is analyzed by multi-timescale methods that study Markov chains obtained via policy update dynamics. This work extends the applicability of the decentralized Q-learning algorithm and its relatives to settings in which parameters are selected in an independent manner, and tames non-stationarity without imposing the coordination assumptions of prior work.

arXiv:2308.01490

Minimax Optimal Q Learning with Nearest Neighbors

Analyzing the Markov decision process (MDP) with continuous state spaces is generally challenging. A recent interesting work \cite{shah2018q} solves MDP with bounded continuous state space by a nearest neighbor $Q$ learning approach, which has a sample complexity of $\tilde{O}(\frac{1}{\epsilon^{d+3}(1-\gamma)^{d+7}})$ for $\epsilon$-accurate $Q$ function estimation with discount factor $\gamma$. In this paper, we propose two new nearest neighbor $Q$ learning methods, one for the offline setting and the other for the online setting. We show that the sample complexities of these two methods are $\tilde{O}(\frac{1}{\epsilon^{d+2}(1-\gamma)^{d+2}})$ and $\tilde{O}(\frac{1}{\epsilon^{d+2}(1-\gamma)^{d+3}})$ for offline and online methods respectively, which significantly improve over existing results and have minimax optimal dependence over $\epsilon$. We achieve such improvement by utilizing the samples more efficiently. In particular, the method in \cite{shah2018q} clears up all samples after each iteration, thus these samples are somewhat wasted. On the other hand, our offline method does not remove any samples, and our online method only removes samples with time earlier than $\beta t$ at time $t$ with $\beta$ being a tunable parameter, thus our methods significantly reduce the loss of information. Apart from the sample complexity, our methods also have additional advantages of better computational complexity, as well as suitability to unbounded state spaces.

arXiv:2307.16212공식 코드 · Papers with Code

Robust Multi-Agent Reinforcement Learning with State Uncertainty

In real-world multi-agent reinforcement learning (MARL) applications, agents may not have perfect state information (e.g., due to inaccurate measurement or malicious attacks), which challenges the robustness of agents' policies. Though robustness is getting important in MARL deployment, little prior work has studied state uncertainties in MARL, neither in problem formulation nor algorithm design. Motivated by this robustness issue and the lack of corresponding studies, we study the problem of MARL with state uncertainty in this work. We provide the first attempt to the theoretical and empirical analysis of this challenging problem. We first model the problem as a Markov Game with state perturbation adversaries (MG-SPA) by introducing a set of state perturbation adversaries into a Markov Game. We then introduce robust equilibrium (RE) as the solution concept of an MG-SPA. We conduct a fundamental analysis regarding MG-SPA such as giving conditions under which such a robust equilibrium exists. Then we propose a robust multi-agent Q-learning (RMAQ) algorithm to find such an equilibrium, with convergence guarantees. To handle high-dimensional state-action space, we design a robust multi-agent actor-critic (RMAAC) algorithm based on an analytical expression of the policy gradient derived in the paper. Our experiments show that the proposed RMAQ algorithm converges to the optimal value function; our RMAAC algorithm outperforms several MARL and robust MARL methods in multiple multi-agent environments when state uncertainty is present. The source code is public on \url{https://github.com/sihongho/robust_marl_with_state_uncertainty}.

arXiv:2307.13922

Stability of Multi-Agent Learning: Convergence in Network Games with Many Players

The behaviour of multi-agent learning in many player games has been shown to display complex dynamics outside of restrictive examples such as network zero-sum games. In addition, it has been shown that convergent behaviour is less likely to occur as the number of players increase. To make progress in resolving this problem, we study Q-Learning dynamics and determine a sufficient condition for the dynamics to converge to a unique equilibrium in any network game. We find that this condition depends on the nature of pairwise interactions and on the network structure, but is explicitly independent of the total number of agents in the game. We evaluate this result on a number of representative network games and show that, under suitable network conditions, stable learning dynamics can be achieved with an arbitrary number of agents.