PyTorchKR Papers

최신 논문

총 1,872편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2210.01231

Interpretable Option Discovery using Deep Q-Learning and Variational Autoencoders

Deep Reinforcement Learning (RL) is unquestionably a robust framework to train autonomous agents in a wide variety of disciplines. However, traditional deep and shallow model-free RL algorithms suffer from low sample efficiency and inadequate generalization for sparse state spaces. The options framework with temporal abstractions is perhaps the most promising method to solve these problems, but it still has noticeable shortcomings. It only guarantees local convergence, and it is challenging to automate initiation and termination conditions, which in practice are commonly hand-crafted. Our proposal, the Deep Variational Q-Network (DVQN), combines deep generative- and reinforcement learning. The algorithm finds good policies from a Gaussian distributed latent-space, which is especially useful for defining options. The DVQN algorithm uses MSE with KL-divergence as regularization, combined with traditional Q-Learning updates. The algorithm learns a latent-space that represents good policies with state clusters for options. We show that the DVQN algorithm is a promising approach for identifying initiation and termination conditions for option-based reinforcement learning. Experiments show that the DVQN algorithm, with automatic initiation and termination, has comparable performance to Rainbow and can maintain stability when trained for extended periods after convergence.

arXiv:2210.00327

Deep Recurrent Q-learning for Energy-constrained Coverage with a Mobile Robot

In this paper, we study the problem of coverage of an environment with an energy-constrained robot in the presence of multiple charging stations. As the robot's on-board power supply is limited, it might not have enough energy to cover all the points in the environment with a single charge. Instead, it will need to stop at one or more charging stations to recharge its battery intermittently. The robot cannot violate the energy constraint, i.e., visit a location with negative available energy. To solve this problem, we propose a deep Q-learning framework that produces a policy to maximize the coverage and minimize the budget violations. Our proposed framework also leverages the memory of a recurrent neural network (RNN) to better suit this multi-objective optimization problem. We have tested the presented framework within a 16 x 16 grid environment having charging stations and various obstacle configurations. Results show that our proposed method finds feasible solutions and outperforms a comparable existing technique.

arXiv:2210.00898공식 코드 · Papers with Code

Robust $Q$-learning Algorithm for Markov Decision Processes under Wasserstein Uncertainty

We present a novel $Q$-learning algorithm tailored to solve distributionally robust Markov decision problems where the corresponding ambiguity set of transition probabilities for the underlying Markov decision process is a Wasserstein ball around a (possibly estimated) reference measure. We prove convergence of the presented algorithm and provide several examples also using real data to illustrate both the tractability of our algorithm as well as the benefits of considering distributional robustness when solving stochastic optimal control problems, in particular when the estimated distributions turn out to be misspecified in practice.

arXiv:2210.00065

Application of Deep Q Learning with Simulation Results for Elevator Optimization

This paper presents a methodology for combining programming and mathematics to optimize elevator wait times. Based on simulated user data generated according to the canonical three-peak model of elevator traffic, we first develop a naive model from an intuitive understanding of the logic behind elevators. We take into consideration a general array of features including capacity, acceleration, and maximum wait time thresholds to adequately model realistic circumstances. Using the same evaluation framework, we proceed to develop a Deep Q Learning model in an attempt to match the hard-coded naive approach for elevator control. Throughout the majority of the paper, we work under a Markov Decision Process (MDP) schema, but later explore how the assumption fails to characterize the highly stochastic overall Elevator Group Control System (EGCS).

arXiv:2210.00750

Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficient

Offline reinforcement learning, which aims at optimizing sequential decision-making strategies with historical data, has been extensively applied in real-life applications. State-Of-The-Art algorithms usually leverage powerful function approximators (e.g. neural networks) to alleviate the sample complexity hurdle for better empirical performances. Despite the successes, a more systematic understanding of the statistical complexity for function approximation remains lacking. Towards bridging the gap, we take a step by considering offline reinforcement learning with differentiable function class approximation (DFA). This function class naturally incorporates a wide range of models with nonlinear/nonconvex structures. Most importantly, we show offline RL with differentiable function approximation is provably efficient by analyzing the pessimistic fitted Q-learning (PFQL) algorithm, and our results provide the theoretical basis for understanding a variety of practical heuristics that rely on Fitted Q-Iteration style design. In addition, we further improve our guarantee with a tighter instance-dependent characterization. We hope our work could draw interest in studying reinforcement learning with differentiable function approximation beyond the scope of current research.

arXiv:2209.15141

On Convergence of Average-Reward Off-Policy Control Algorithms in Weakly Communicating MDPs

We show two average-reward off-policy control algorithms, Differential Q-learning (Wan, Naik, & Sutton 2021a) and RVI Q-learning (Abounadi Bertsekas & Borkar 2001), converge in weakly communicating MDPs. Weakly communicating MDPs are the most general MDPs that can be solved by a learning algorithm with a single stream of experience. The original convergence proofs of the two algorithms require that the solution set of the average-reward optimality equation only has one degree of freedom, which is not necessarily true for weakly communicating MDPs. To the best of our knowledge, our results are the first showing average-reward off-policy control algorithms converge in weakly communicating MDPs. As a direct extension, we show that average-reward options algorithms for temporal abstraction introduced by Wan, Naik, & Sutton (2021b) converge if the Semi-MDP induced by options is weakly communicating.

arXiv:2209.15502

Efficient LSTM Training with Eligibility Traces

Training recurrent neural networks is predominantly achieved via backpropagation through time (BPTT). However, this algorithm is not an optimal solution from both a biological and computational perspective. A more efficient and biologically plausible alternative for BPTT is e-prop. We investigate the applicability of e-prop to long short-term memorys (LSTMs), for both supervised and reinforcement learning (RL) tasks. We show that e-prop is a suitable optimization algorithm for LSTMs by comparing it to BPTT on two benchmarks for supervised learning. This proves that e-prop can achieve learning even for problems with long sequences of several hundred timesteps. We introduce extensions that improve the performance of e-prop, which can partially be applied to other network architectures. With the help of these extensions we show that, under certain conditions, e-prop can outperform BPTT for one of the two benchmarks for supervised learning. Finally, we deliver a proof of concept for the integration of e-prop to RL in the domain of deep recurrent Q-learning.

arXiv:2209.14399

FIRE: A Failure-Adaptive Reinforcement Learning Framework for Edge Computing Migrations

In edge computing, users' service profiles are migrated due to user mobility. Reinforcement learning (RL) frameworks have been proposed to do so, often trained on simulated data. However, existing RL frameworks overlook occasional server failures, which although rare, impact latency-sensitive applications like autonomous driving and real-time obstacle detection. Nevertheless, these failures (rare events), being not adequately represented in historical training data, pose a challenge for data-driven RL algorithms. As it is impractical to adjust failure frequency in real-world applications for training, we introduce FIRE, a framework that adapts to rare events by training a RL policy in an edge computing digital twin environment. We propose ImRE, an importance sampling-based Q-learning algorithm, which samples rare events proportionally to their impact on the value function. FIRE considers delay, migration, failure, and backup placement costs across individual and shared service profiles. We prove ImRE's boundedness and convergence to optimality. Next, we introduce novel deep Q-learning (ImDQL) and actor critic (ImACRE) versions of our algorithm to enhance scalability. We extend our framework to accommodate users with varying risk tolerances. Through trace driven experiments, we show that FIRE reduces costs compared to vanilla RL and the greedy baseline in the event of failures.

arXiv:2209.13046

Understanding Hindsight Goal Relabeling from a Divergence Minimization Perspective

Hindsight goal relabeling has become a foundational technique in multi-goal reinforcement learning (RL). The essential idea is that any trajectory can be seen as a sub-optimal demonstration for reaching its final state. Intuitively, learning from those arbitrary demonstrations can be seen as a form of imitation learning (IL). However, the connection between hindsight goal relabeling and imitation learning is not well understood. In this paper, we propose a novel framework to understand hindsight goal relabeling from a divergence minimization perspective. Recasting the goal reaching problem in the IL framework not only allows us to derive several existing methods from first principles, but also provides us with the tools from IL to improve goal reaching algorithms. Experimentally, we find that under hindsight relabeling, Q-learning outperforms behavioral cloning (BC). Yet, a vanilla combination of both hurts performance. Concretely, we see that the BC loss only helps when selectively applied to actions that get the agent closer to the goal according to the Q-function. Our framework also explains the puzzling phenomenon wherein a reward of (-1, 0) results in significantly better performance than a (0, 1) reward for goal reaching.

arXiv:2209.10081공식 코드 · Papers with Code

Revisiting Discrete Soft Actor-Critic

We study the adaption of Soft Actor-Critic (SAC), which is considered as a state-of-the-art reinforcement learning (RL) algorithm, from continuous action space to discrete action space. We revisit vanilla discrete SAC and provide an in-depth understanding of its Q value underestimation and performance instability issues when applied to discrete settings. We thereby propose Stable Discrete SAC (SDSAC), an algorithm that leverages entropy-penalty and double average Q-learning with Q-clip to address these issues. Extensive experiments on typical benchmarks with discrete action space, including Atari games and a large-scale MOBA game, show the efficacy of our proposed method. Our code is at: https://github.com/coldsummerday/SD-SAC.git.

arXiv:2209.09329공식 코드 · Papers with Code

MAN: Multi-Action Networks Learning

Learning control policies with large discrete action spaces is a challenging problem in the field of reinforcement learning due to present inefficiencies in exploration. With high dimensional action spaces, there are a large number of potential actions in each individual dimension over which policies would be learned. In this work, we introduce a Deep Reinforcement Learning (DRL) algorithm call Multi-Action Networks (MAN) Learning that addresses the challenge of high-dimensional large discrete action spaces. We propose factorizing the N-dimension action space into N 1-dimensional components, known as sub-actions, creating a Value Neural Network for each sub-action. Then, MAN uses temporal-difference learning to train the networks synchronously, which is simpler than training a single network with a large action output directly. To evaluate the proposed method, we test MAN on three scenarios: an n-dimension maze task, a block stacking task, and then extend MAN to handle 12 games from the Atari Arcade Learning environment with 18 action spaces. Our results indicate that MAN learns faster than both Deep Q-Learning and Double Deep Q-Learning, implying our method is a better performing synchronous temporal difference algorithm than those currently available for large discrete action spaces.

arXiv:2209.08244

MA2QL: A Minimalist Approach to Fully Decentralized Multi-Agent Reinforcement Learning

Decentralized learning has shown great promise for cooperative multi-agent reinforcement learning (MARL). However, non-stationarity remains a significant challenge in fully decentralized learning. In the paper, we tackle the non-stationarity problem in the simplest and fundamental way and propose multi-agent alternate Q-learning (MA2QL), where agents take turns updating their Q-functions by Q-learning. MA2QL is a minimalist approach to fully decentralized cooperative MARL but is theoretically grounded. We prove that when each agent guarantees $\varepsilon$-convergence at each turn, their joint policy converges to a Nash equilibrium. In practice, MA2QL only requires minimal changes to independent Q-learning (IQL). We empirically evaluate MA2QL on a variety of cooperative multi-agent tasks. Results show MA2QL consistently outperforms IQL, which verifies the effectiveness of MA2QL, despite such minimal changes.

arXiv:2209.09007

Comparative Study of Q-Learning and NeuroEvolution of Augmenting Topologies for Self Driving Agents

Autonomous driving vehicles have been of keen interest ever since automation of various tasks started. Humans are prone to exhaustion and have a slow response time on the road, and on top of that driving is already quite a dangerous task with around 1.35 million road traffic incident deaths each year. It is expected that autonomous driving can reduce the number of driving accidents around the world which is why this problem has been of keen interest for researchers. Currently, self-driving vehicles use different algorithms for various sub-problems in making the vehicle autonomous. We will focus reinforcement learning algorithms, more specifically Q-learning algorithms and NeuroEvolution of Augment Topologies (NEAT), a combination of evolutionary algorithms and artificial neural networks, to train a model agent to learn how to drive on a given path. This paper will focus on drawing a comparison between the two aforementioned algorithms.

arXiv:2209.07744

Reinforcement Learning-Based Cooperative P2P Power Trading between DC Nanogrid Clusters with Wind and PV Energy Resources

In replacing fossil fuels with renewable energy resources for carbon neutrality, the unbalanced resource production of intermittent wind and photovoltaic (PV) power is a critical issue for peer-to-peer (P2P) power trading. To address this issue, a reinforcement learning (RL) technique is introduced in this paper. For RL, a graph convolutional network (GCN) and a bi-directional long short-term memory (Bi-LSTM) network are jointly applied to P2P power trading between nanogrid clusters, based on cooperative game theory. The flexible and reliable DC nanogrid is suitable for integrating renewable energy for a distribution system. Each local nanogrid cluster takes the position of prosumer, focusing on power production and consumption simultaneously. For the power management of nanogrid cluster, multi-objective optimization is applied to each local nanogrid cluster with the Internet of Things (IoT) technology. Charging/discharging of an electric vehicle (EV) is executed considering the intermittent characteristics of wind and PV power production. RL algorithms, such as GCN- convolutional neural network (CNN) layers for deep Q-learning network (DQN), GCN-LSTM layers for deep recurrent Q-learning network (DRQN), GCN-Bi-LSTM layers for DRQN, and GCN-Bi-LSTM layers for proximal policy optimization (PPO), are used for simulations. Consequently, the cooperative P2P power trading system maximizes the profit by considering the time of use (ToU) tariff-based electricity cost and the system marginal price (SMP), and minimizes the amount of grid power consumption. Power management of nanogrid clusters with P2P power trading is simulated on a distribution test feeder in real time, and the proposed GCN-Bi-LSTM-PPO technique achieving the lowest electricity cost among the RL algorithms used for comparison reduces the electricity cost by 36.7%, averaging over nanogrid clusters.

arXiv:2209.07809공식 코드 · Papers with Code

M$^2$DQN: A Robust Method for Accelerating Deep Q-learning Network

Deep Q-learning Network (DQN) is a successful way which combines reinforcement learning with deep neural networks and leads to a widespread application of reinforcement learning. One challenging problem when applying DQN or other reinforcement learning algorithms to real world problem is data collection. Therefore, how to improve data efficiency is one of the most important problems in the research of reinforcement learning. In this paper, we propose a framework which uses the Max-Mean loss in Deep Q-Network (M$^2$DQN). Instead of sampling one batch of experiences in the training step, we sample several batches from the experience replay and update the parameters such that the maximum TD-error of these batches is minimized. The proposed method can be combined with most of existing techniques of DQN algorithm by replacing the loss function. We verify the effectiveness of this framework with one of the most widely used techniques, Double DQN (DDQN), in several gym games. The results show that our method leads to a substantial improvement in both the learning speed and performance.

arXiv:2209.07382

IoT-Aerial Base Station Task Offloading with Risk-Sensitive Reinforcement Learning for Smart Agriculture

Aerial base stations (ABSs) allow smart farms to offload processing responsibility of complex tasks from internet of things (IoT) devices to ABSs. IoT devices have limited energy and computing resources, thus it is required to provide an advanced solution for a system that requires the support of ABSs. This paper introduces a novel multi-actor-based risk-sensitive reinforcement learning approach for ABS task scheduling for smart agriculture. The problem is defined as task offloading with a strict condition on completing the IoT tasks before their deadlines. Moreover, the algorithm must also consider the limited energy capacity of the ABSs. The results show that our proposed approach outperforms several heuristics and the classic Q-Learning approach. Furthermore, we provide a mixed integer linear programming solution to determine a lower bound on the performance, and clarify the gap between our risk-sensitive solution and the optimal solution, as well. The comparison proves our extensive simulation results demonstrate that our method is a promising approach for providing a guaranteed task processing services for the IoT tasks in a smart farm, while increasing the hovering time of the ABSs in this farm.

arXiv:2209.07367

Deep Reinforcement Learning for Task Offloading in UAV-Aided Smart Farm Networks

The fifth and sixth generations of wireless communication networks are enabling tools such as internet of things devices, unmanned aerial vehicles (UAVs), and artificial intelligence, to improve the agricultural landscape using a network of devices to automatically monitor farmlands. Surveying a large area requires performing a lot of image classification tasks within a specific period of time in order to prevent damage to the farm in case of an incident, such as fire or flood. UAVs have limited energy and computing power, and may not be able to perform all of the intense image classification tasks locally and within an appropriate amount of time. Hence, it is assumed that the UAVs are able to partially offload their workload to nearby multi-access edge computing devices. The UAVs need a decision-making algorithm that will decide where the tasks will be performed, while also considering the time constraints and energy level of the other UAVs in the network. In this paper, we introduce a Deep Q-Learning (DQL) approach to solve this multi-objective problem. The proposed method is compared with Q-Learning and three heuristic baselines, and the simulation results show that our proposed DQL-based method achieves comparable results when it comes to the UAVs' remaining battery levels and percentage of deadline violations. In addition, our method is able to reach convergence 13 times faster than Q-Learning.

arXiv:2209.04698

Structured Q-learning For Antibody Design

Optimizing combinatorial structures is core to many real-world problems, such as those encountered in life sciences. For example, one of the crucial steps involved in antibody design is to find an arrangement of amino acids in a protein sequence that improves its binding with a pathogen. Combinatorial optimization of antibodies is difficult due to extremely large search spaces and non-linear objectives. Even for modest antibody design problems, where proteins have a sequence length of eleven, we are faced with searching over 2.05 x 10^14 structures. Applying traditional Reinforcement Learning algorithms such as Q-learning to combinatorial optimization results in poor performance. We propose Structured Q-learning (SQL), an extension of Q-learning that incorporates structural priors for combinatorial optimization. Using a molecular docking simulator, we demonstrate that SQL finds high binding energy sequences and performs favourably against baselines on eight challenging antibody design tasks, including designing antibodies for SARS-COV.

arXiv:2209.03993공식 코드 · Papers with Code

Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL

Recent works have shown that tackling offline reinforcement learning (RL) with a conditional policy produces promising results. The Decision Transformer (DT) combines the conditional policy approach and a transformer architecture, showing competitive performance against several benchmarks. However, DT lacks stitching ability -- one of the critical abilities for offline RL to learn the optimal policy from sub-optimal trajectories. This issue becomes particularly significant when the offline dataset only contains sub-optimal trajectories. On the other hand, the conventional RL approaches based on Dynamic Programming (such as Q-learning) do not have the same limitation; however, they suffer from unstable learning behaviours, especially when they rely on function approximation in an off-policy learning setting. In this paper, we propose the Q-learning Decision Transformer (QDT) to address the shortcomings of DT by leveraging the benefits of Dynamic Programming (Q-learning). It utilises the Dynamic Programming results to relabel the return-to-go in the training data to then train the DT with the relabelled data. Our approach efficiently exploits the benefits of these two approaches and compensates for each other's shortcomings to achieve better performance. We empirically show these in both simple toy environments and the more complex D4RL benchmark, showing competitive performance gains.

arXiv:2209.04265공식 코드 · Papers with Code

Route Planning for Last-Mile Deliveries Using Mobile Parcel Lockers: A Hybrid Q-Learning Network Approach

Mobile parcel lockers have been recently proposed by logistics operators as a technology that could help reduce traffic congestion and operational costs in urban freight distribution. Given their ability to relocate throughout their area of deployment, they hold the potential to improve customer accessibility and convenience. In this study, we formulate the Mobile Parcel Locker Problem (MPLP) , a special case of the Location-Routing Problem (LRP) which determines the optimal stopover location for MPLs throughout the day and plans corresponding delivery routes. A Hybrid Q Learning Network based Method (HQM) is developed to resolve the computational complexity of the resulting large problem instances while escaping local optima. In addition, the HQM is integrated with global and local search mechanisms to resolve the dilemma of exploration and exploitation faced by classic reinforcement learning methods. We examine the performance of HQM under different problem sizes (up to 200 nodes) and benchmarked it against the exact approach and Genetic Algorithm (GA). Our results indicate that HQM achieves better optimisation performance with shorter computation time than the exact approach solved by the Gurobi solver in large problem instances. Additionally, the average reward obtained by HQM is 1.96 times greater than GA, which demonstrates that HQM has a better optimisation ability. Further, we identify critical factors that contribute to fleet size requirements, travel distances, and service delays. Our findings outline that the efficiency of MPLs is mainly contingent on the length of time windows and the deployment of MPL stopovers. Finally, we highlight managerial implications based on parametric analysis to provide guidance for logistics operators in the context of efficient last-mile distribution operations.