PyTorchKR Papers

최신 논문

총 1,873편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2402.12049

Reinforcement Learning for Optimal Execution when Liquidity is Time-Varying

Optimal execution is an important problem faced by any trader. Most solutions are based on the assumption of constant market impact, while liquidity is known to be dynamic. Moreover, models with time-varying liquidity typically assume that it is observable, despite the fact that, in reality, it is latent and hard to measure in real time. In this paper we show that the use of Double Deep Q-learning, a form of Reinforcement Learning based on neural networks, is able to learn optimal trading policies when liquidity is time-varying. Specifically, we consider an Almgren-Chriss framework with temporary and permanent impact parameters following several deterministic and stochastic dynamics. Using extensive numerical experiments, we show that the trained algorithm learns the optimal policy when the analytical solution is available, and overcomes benchmarks and approximated solutions when the solution is not available.

arXiv:2402.13147공식 코드 · Papers with Code

SPRINQL: Sub-optimal Demonstrations driven Offline Imitation Learning

We focus on offline imitation learning (IL), which aims to mimic an expert's behavior using demonstrations without any interaction with the environment. One of the main challenges in offline IL is the limited support of expert demonstrations, which typically cover only a small fraction of the state-action space. While it may not be feasible to obtain numerous expert demonstrations, it is often possible to gather a larger set of sub-optimal demonstrations. For example, in treatment optimization problems, there are varying levels of doctor treatments available for different chronic conditions. These range from treatment specialists and experienced general practitioners to less experienced general practitioners. Similarly, when robots are trained to imitate humans in routine tasks, they might learn from individuals with different levels of expertise and efficiency. In this paper, we propose an offline IL approach that leverages the larger set of sub-optimal demonstrations while effectively mimicking expert trajectories. Existing offline IL methods based on behavior cloning or distribution matching often face issues such as overfitting to the limited set of expert demonstrations or inadvertently imitating sub-optimal trajectories from the larger dataset. Our approach, which is based on inverse soft-Q learning, learns from both expert and sub-optimal demonstrations. It assigns higher importance (through learned weights) to aligning with expert demonstrations and lower importance to aligning with sub-optimal ones. A key contribution of our approach, called SPRINQL, is transforming the offline IL problem into a convex optimization over the space of Q functions. Through comprehensive experimental evaluations, we demonstrate that the SPRINQL algorithm achieves state-of-the-art (SOTA) performance on offline IL benchmarks. Code is available at https://github.com/hmhuy0/SPRINQL.

arXiv:2402.12015

An Index Policy Based on Sarsa and Q-learning for Heterogeneous Smart Target Tracking

In solving the non-myopic radar scheduling for multiple smart target tracking within an active and passive radar network, we need to consider both short-term enhanced tracking performance and a higher probability of target maneuvering in the future with active tracking. Acquiring the long-term tracking performance while scheduling the beam resources of active and passive radars poses a challenge. To address this challenge, we model this problem as a Markov decision process consisting of parallel restless bandit processes. Each bandit process is associated with a smart target, of which the estimation state evolves according to different discrete dynamic models for different actions - whether or not the target is being tracked. The discrete state is defined by the dynamic mode. The problem exhibits the curse of dimensionality, where optimal solutions are in general intractable. We resort to heuristics through the famous restless multi-armed bandit techniques. It follows with efficient scheduling policies based on the indices that are real numbers representing the marginal rewards of taking different actions. For the inevitable practical case with unknown transition matrices, we propose a new method that utilizes the forward Sarsa and backward Q-learning to approximate the indices through adapting the state-action value functions, or equivalently the Q-functions, and propose a new policy, namely ISQ, aiming to maximize the long-term tracking rewards. Numerical results demonstrate that the proposed ISQ policy outperforms conventional Q-learning-based methods and rapidly converges to the well-known Whittle index policy with revealed state transition models, which is considered the benchmark.

arXiv:2402.11835

Easy as ABCs: Unifying Boltzmann Q-Learning and Counterfactual Regret Minimization

We propose ABCs (Adaptive Branching through Child stationarity), a best-of-both-worlds algorithm combining Boltzmann Q-learning (BQL), a classic reinforcement learning algorithm for single-agent domains, and counterfactual regret minimization (CFR), a central algorithm for learning in multi-agent domains. ABCs adaptively chooses what fraction of the environment to explore each iteration by measuring the stationarity of the environment's reward and transition dynamics. In Markov decision processes, ABCs converges to the optimal policy with at most an O(A) factor slowdown compared to BQL, where A is the number of actions in the environment. In two-player zero-sum games, ABCs is guaranteed to converge to a Nash equilibrium (assuming access to a perfect oracle for detecting stationarity), while BQL has no such guarantees. Empirically, ABCs demonstrates strong performance when benchmarked across environments drawn from the OpenSpiel game library and OpenAI Gym and exceeds all prior methods in environments which are neither fully stationary nor fully nonstationary.

arXiv:2402.11384

Reinforcement learning to maximise wind turbine energy generation

We propose a reinforcement learning strategy to control wind turbine energy generation by actively changing the rotor speed, the rotor yaw angle and the blade pitch angle. A double deep Q-learning with a prioritized experience replay agent is coupled with a blade element momentum model and is trained to allow control for changing winds. The agent is trained to decide the best control (speed, yaw, pitch) for simple steady winds and is subsequently challenged with real dynamic turbulent winds, showing good performance. The double deep Q- learning is compared with a classic value iteration reinforcement learning control and both strategies outperform a classic PID control in all environments. Furthermore, the reinforcement learning approach is well suited to changing environments including turbulent/gusty winds, showing great adaptability. Finally, we compare all control strategies with real winds and compute the annual energy production. In this case, the double deep Q-learning algorithm also outperforms classic methodologies.

arXiv:2402.11877

Finite-Time Error Analysis of Online Model-Based Q-Learning with a Relaxed Sampling Model

Reinforcement learning has witnessed significant advancements, particularly with the emergence of model-based approaches. Among these, $Q$-learning has proven to be a powerful algorithm in model-free settings. However, the extension of $Q$-learning to a model-based framework remains relatively unexplored. In this paper, we delve into the sample complexity of $Q$-learning when integrated with a model-based approach. Through theoretical analyses and empirical evaluations, we seek to elucidate the conditions under which model-based $Q$-learning excels in terms of sample efficiency compared to its model-free counterpart.

arXiv:2402.11800

Stochastic Approximation with Delayed Updates: Finite-Time Rates under Markovian Sampling

Motivated by applications in large-scale and multi-agent reinforcement learning, we study the non-asymptotic performance of stochastic approximation (SA) schemes with delayed updates under Markovian sampling. While the effect of delays has been extensively studied for optimization, the manner in which they interact with the underlying Markov process to shape the finite-time performance of SA remains poorly understood. In this context, our first main contribution is to show that under time-varying bounded delays, the delayed SA update rule guarantees exponentially fast convergence of the \emph{last iterate} to a ball around the SA operator's fixed point. Notably, our bound is \emph{tight} in its dependence on both the maximum delay $\tau_{max}$, and the mixing time $\tau_{mix}$. To achieve this tight bound, we develop a novel inductive proof technique that, unlike various existing delayed-optimization analyses, relies on establishing uniform boundedness of the iterates. As such, our proof may be of independent interest. Next, to mitigate the impact of the maximum delay on the convergence rate, we provide the first finite-time analysis of a delay-adaptive SA scheme under Markovian sampling. In particular, we show that the exponent of convergence of this scheme gets scaled down by $\tau_{avg}$, as opposed to $\tau_{max}$ for the vanilla delayed SA rule; here, $\tau_{avg}$ denotes the average delay across all iterations. Moreover, the adaptive scheme requires no prior knowledge of the delay sequence for step-size tuning. Our theoretical findings shed light on the finite-time effects of delays for a broad class of algorithms, including TD learning, Q-learning, and stochastic gradient descent under Markovian sampling.

arXiv:2402.09078

Exploiting Estimation Bias in Clipped Double Q-Learning for Continous Control Reinforcement Learning Tasks

Continuous control Deep Reinforcement Learning (RL) approaches are known to suffer from estimation biases, leading to suboptimal policies. This paper introduces innovative methods in RL, focusing on addressing and exploiting estimation biases in Actor-Critic methods for continuous control tasks, using Deep Double Q-Learning. We design a Bias Exploiting (BE) mechanism to dynamically select the most advantageous estimation bias during training of the RL agent. Most State-of-the-art Deep RL algorithms can be equipped with the BE mechanism, without hindering performance or computational complexity. Our extensive experiments across various continuous control tasks demonstrate the effectiveness of our approaches. We show that RL algorithms equipped with this method can match or surpass their counterparts, particularly in environments where estimation biases significantly impact learning. The results underline the importance of bias exploitation in improving policy learning in RL.

arXiv:2402.08832

Intelligent Agricultural Management Considering N$_2$O Emission and Climate Variability with Uncertainties

This study examines how artificial intelligence (AI), especially Reinforcement Learning (RL), can be used in farming to boost crop yields, fine-tune nitrogen use and watering, and reduce nitrate runoff and greenhouse gases, focusing on Nitrous Oxide (N$_2$O) emissions from soil. Facing climate change and limited agricultural knowledge, we use Partially Observable Markov Decision Processes (POMDPs) with a crop simulator to model AI agents' interactions with farming environments. We apply deep Q-learning with Recurrent Neural Network (RNN)-based Q networks for training agents on optimal actions. Also, we develop Machine Learning (ML) models to predict N$_2$O emissions, integrating these predictions into the simulator. Our research tackles uncertainties in N$_2$O emission estimates with a probabilistic ML approach and climate variability through a stochastic weather model, offering a range of emission outcomes to improve forecast reliability and decision-making. By incorporating climate change effects, we enhance agents' climate adaptability, aiming for resilient agricultural practices. Results show these agents can align crop productivity with environmental concerns by penalizing N$_2$O emissions, adapting effectively to climate shifts like warmer temperatures and less rain. This strategy improves farm management under climate change, highlighting AI's role in sustainable agriculture.

arXiv:2402.08780

Enhanced Deep Q-Learning for 2D Self-Driving Cars: Implementation and Evaluation on a Custom Track Environment

This research project presents the implementation of a Deep Q-Learning Network (DQN) for a self-driving car on a 2-dimensional (2D) custom track, with the objective of enhancing the DQN network's performance. It encompasses the development of a custom driving environment using Pygame on a track surrounding the University of Memphis map, as well as the design and implementation of the DQN model. The algorithm utilizes data from 7 sensors installed in the car, which measure the distance between the car and the track. These sensors are positioned in front of the vehicle, spaced 20 degrees apart, enabling them to sense a wide area ahead. We successfully implemented the DQN and also a modified version of the DQN with a priority-based action selection mechanism, which we refer to as modified DQN. The model was trained over 1000 episodes, and the average reward received by the agent was found to be around 40, which is approximately 60% higher than the original DQN and around 50% higher than the vanilla neural network.

arXiv:2402.08022공식 코드 · Papers with Code

Leveraging Digital Cousins for Ensemble Q-Learning in Large-Scale Wireless Networks

Optimizing large-scale wireless networks, including optimal resource management, power allocation, and throughput maximization, is inherently challenging due to their non-observable system dynamics and heterogeneous and complex nature. Herein, a novel ensemble Q-learning algorithm that addresses the performance and complexity challenges of the traditional Q-learning algorithm for optimizing wireless networks is presented. Ensemble learning with synthetic Markov Decision Processes is tailored to wireless networks via new models for approximating large state-space observable wireless networks. In particular, digital cousins are proposed as an extension of the traditional digital twin concept wherein multiple Q-learning algorithms on multiple synthetic Markovian environments are run in parallel and their outputs are fused into a single Q-function. Convergence analyses of key statistics and Q-functions and derivations of upper bounds on the estimation bias and variance are provided. Numerical results across a variety of real-world wireless networks show that the proposed algorithm can achieve up to 50% less average policy error with up to 40% less runtime complexity than the state-of-the-art reinforcement learning algorithms. It is also shown that theoretical results properly predict trends in the experimental results.

arXiv:2402.08421공식 코드 · Papers with Code

Conservative and Risk-Aware Offline Multi-Agent Reinforcement Learning

Reinforcement learning (RL) has been widely adopted for controlling and optimizing complex engineering systems such as next-generation wireless networks. An important challenge in adopting RL is the need for direct access to the physical environment. This limitation is particularly severe in multi-agent systems, for which conventional multi-agent reinforcement learning (MARL) requires a large number of coordinated online interactions with the environment during training. When only offline data is available, a direct application of online MARL schemes would generally fail due to the epistemic uncertainty entailed by the lack of exploration during training. In this work, we propose an offline MARL scheme that integrates distributional RL and conservative Q-learning to address the environment's inherent aleatoric uncertainty and the epistemic uncertainty arising from the use of offline data. We explore both independent and joint learning strategies. The proposed MARL scheme, referred to as multi-agent conservative quantile regression, addresses general risk-sensitive design criteria and is applied to the trajectory planning problem in drone networks, showcasing its advantages.

arXiv:2402.06931

ORIENT: A Priority-Aware Energy-Efficient Approach for Latency-Sensitive Applications in 6G

Anticipation for 6G's arrival comes with growing concerns about increased energy consumption in computing and networking. The expected surge in connected devices and resource-demanding applications presents unprecedented challenges for energy resources. While sustainable resource allocation strategies have been discussed in the past, these efforts have primarily focused on single-domain orchestration or ignored the unique requirements posed by 6G. To address this gap, we investigate the joint problem of service instance placement and assignment, path selection, and request prioritization, dubbed PIRA. The objective function is to maximize the system's overall profit as a function of the number of concurrently supported requests while simultaneously minimizing energy consumption over an extended period of time. In addition, end-to-end latency requirements and resource capacity constraints are considered for computing and networking resources, where queuing theory is utilized to estimate the Age of Information (AoI) for requests. After formulating the problem in a non-linear fashion, we prove its NP-hardness and propose a method, denoted ORIENT. This method is based on the Double Dueling Deep Q-Learning (D3QL) mechanism and leverages Graph Neural Networks (GNNs) for state encoding. Extensive numerical simulations demonstrate that ORIENT yields near-optimal solutions for varying system sizes and request counts.

arXiv:2402.06912공식 코드 · Papers with Code

Solving Deep Reinforcement Learning Tasks with Evolution Strategies and Linear Policy Networks

Although deep reinforcement learning methods can learn effective policies for challenging problems such as Atari games and robotics tasks, algorithms are complex, and training times are often long. This study investigates how Evolution Strategies perform compared to gradient-based deep reinforcement learning methods. We use Evolution Strategies to optimize the weights of a neural network via neuroevolution, performing direct policy search. We benchmark both deep policy networks and networks consisting of a single linear layer from observations to actions for three gradient-based methods, such as Proximal Policy Optimization. These methods are evaluated against three classical Evolution Strategies and Augmented Random Search, which all use linear policy networks. Our results reveal that Evolution Strategies can find effective linear policies for many reinforcement learning benchmark tasks, unlike deep reinforcement learning methods that can only find successful policies using much larger networks, suggesting that current benchmarks are easier to solve than previously assumed. Interestingly, Evolution Strategies also achieve results comparable to gradient-based deep reinforcement learning algorithms for higher-complexity tasks. Furthermore, we find that by directly accessing the memory state of the game, Evolution Strategies can find successful policies in Atari that outperform the policies found by Deep Q-Learning. Evolution Strategies also outperform Augmented Random Search in most benchmarks, demonstrating superior sample efficiency and robustness in training linear policy networks.

arXiv:2402.05951

MinMaxMin $Q$-learning

MinMaxMin $Q$-learning is a novel optimistic Actor-Critic algorithm that addresses the problem of overestimation bias ($Q$-estimations are overestimating the real $Q$-values) inherent in conservative RL algorithms. Its core formula relies on the disagreement among $Q$-networks in the form of the min-batch MaxMin $Q$-networks distance which is added to the $Q$-target and used as the priority experience replay sampling-rule. We implement MinMaxMin on top of TD3 and TD7, subjecting it to rigorous testing against state-of-the-art continuous-space algorithms-DDPG, TD3, and TD7-across popular MuJoCo and Bullet environments. The results show a consistent performance improvement of MinMaxMin over DDPG, TD3, and TD7 across all tested tasks.

arXiv:2402.05950

SQT -- std $Q$-target

Std $Q$-target is a conservative, actor-critic, ensemble, $Q$-learning-based algorithm, which is based on a single key $Q$-formula: $Q$-networks standard deviation, which is an "uncertainty penalty", and, serves as a minimalistic solution to the problem of overestimation bias. We implement SQT on top of TD3/TD7 code and test it against the state-of-the-art (SOTA) actor-critic algorithms, DDPG, TD3 and TD7 on seven popular MuJoCo and Bullet tasks. Our results demonstrate SQT's $Q$-target formula superiority over TD3's $Q$-target formula as a conservative solution to overestimation bias in RL, while SQT shows a clear performance advantage on a wide margin over DDPG, TD3, and TD7 on all tasks.

arXiv:2402.06266

Value function interference and greedy action selection in value-based multi-objective reinforcement learning

Multi-objective reinforcement learning (MORL) algorithms extend conventional reinforcement learning (RL) to the more general case of problems with multiple, conflicting objectives, represented by vector-valued rewards. Widely-used scalar RL methods such as Q-learning can be modified to handle multiple objectives by (1) learning vector-valued value functions, and (2) performing action selection using a scalarisation or ordering operator which reflects the user's utility with respect to the different objectives. However, as we demonstrate here, if the user's utility function maps widely varying vector-values to similar levels of utility, this can lead to interference in the value-function learned by the agent, leading to convergence to sub-optimal policies. This will be most prevalent in stochastic environments when optimising for the Expected Scalarised Return criterion, but we present a simple example showing that interference can also arise in deterministic environments. We demonstrate empirically that avoiding the use of random tie-breaking when identifying greedy actions can ameliorate, but not fully overcome, the problems caused by value function interference.

arXiv:2402.05876

Federated Offline Reinforcement Learning: Collaborative Single-Policy Coverage Suffices

Offline reinforcement learning (RL), which seeks to learn an optimal policy using offline data, has garnered significant interest due to its potential in critical applications where online data collection is infeasible or expensive. This work explores the benefit of federated learning for offline RL, aiming at collaboratively leveraging offline datasets at multiple agents. Focusing on finite-horizon episodic tabular Markov decision processes (MDPs), we design FedLCB-Q, a variant of the popular model-free Q-learning algorithm tailored for federated offline RL. FedLCB-Q updates local Q-functions at agents with novel learning rate schedules and aggregates them at a central server using importance averaging and a carefully designed pessimistic penalty term. Our sample complexity analysis reveals that, with appropriately chosen parameters and synchronization schedules, FedLCB-Q achieves linear speedup in terms of the number of agents without requiring high-quality datasets at individual agents, as long as the local datasets collectively cover the state-action space visited by the optimal policy, highlighting the power of collaboration in the federated setting. In fact, the sample complexity almost matches that of the single-agent counterpart, as if all the data are stored at a central location, up to polynomial factors of the horizon length. Furthermore, FedLCB-Q is communication-efficient, where the number of communication rounds is only linear with respect to the horizon length up to logarithmic factors.

arXiv:2402.05476공식 코드 · Papers with Code

Multi-Timescale Ensemble Q-learning for Markov Decision Process Policy Optimization

Reinforcement learning (RL) is a classical tool to solve network control or policy optimization problems in unknown environments. The original Q-learning suffers from performance and complexity challenges across very large networks. Herein, a novel model-free ensemble reinforcement learning algorithm which adapts the classical Q-learning is proposed to handle these challenges for networks which admit Markov decision process (MDP) models. Multiple Q-learning algorithms are run on multiple, distinct, synthetically created and structurally related Markovian environments in parallel; the outputs are fused using an adaptive weighting mechanism based on the Jensen-Shannon divergence (JSD) to obtain an approximately optimal policy with low complexity. The theoretical justification of the algorithm, including the convergence of key statistics and Q-functions are provided. Numerical results across several network models show that the proposed algorithm can achieve up to 55% less average policy error with up to 50% less runtime complexity than the state-of-the-art Q-learning algorithms. Numerical results validate assumptions made in the theoretical analysis.

arXiv:2402.04515

A Deep Reinforcement Learning Approach for Adaptive Traffic Routing in Next-gen Networks

Next-gen networks require significant evolution of management to enable automation and adaptively adjust network configuration based on traffic dynamics. The advent of software-defined networking (SDN) and programmable switches enables flexibility and programmability. However, traditional techniques that decide traffic policies are usually based on hand-crafted programming optimization and heuristic algorithms. These techniques make non-realistic assumptions, e.g., considering static network load and topology, to obtain tractable solutions, which are inadequate for next-gen networks. In this paper, we design and develop a deep reinforcement learning (DRL) approach for adaptive traffic routing. We design a deep graph convolutional neural network (DGCNN) integrated into the DRL framework to learn the traffic behavior from not only the network topology but also link and node attributes. We adopt the Deep Q-Learning technique to train the DGCNN model in the DRL framework without the need for a labeled training dataset, enabling the framework to quickly adapt to traffic dynamics. The model leverages q-value estimates to select the routing path for every traffic flow request, balancing exploration and exploitation. We perform extensive experiments with various traffic patterns and compare the performance of the proposed approach with the Open Shortest Path First (OSPF) protocol. The experimental results show the effectiveness and adaptiveness of the proposed framework by increasing the network throughput by up to 7.8% and reducing the traffic delay by up to 16.1% compared to OSPF.