PyTorchKR Papers

최신 논문

총 6,055편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2405.07175

On-Demand Model and Client Deployment in Federated Learning with Deep Reinforcement Learning

In Federated Learning (FL), the limited accessibility of data from diverse locations and user types poses a significant challenge due to restricted user participation. Expanding client access and diversifying data enhance models by incorporating diverse perspectives, thereby enhancing adaptability. However, challenges arise in dynamic and mobile environments where certain devices may become inaccessible as FL clients, impacting data availability and client selection methods. To address this, we propose an On-Demand solution, deploying new clients using Docker Containers on-the-fly. Our On-Demand solution, employing Deep Reinforcement Learning (DRL), targets client availability and selection, while considering data shifts, and container deployment complexities. It employs an autonomous end-to-end solution for handling model deployment and client selection. The DRL strategy uses a Markov Decision Process (MDP) framework, with a Master Learner and a Joiner Learner. The designed cost functions represent the complexity of the dynamic client deployment and selection. Simulated tests show that our architecture can easily adjust to changes in the environment and respond to On-Demand requests. This underscores its ability to improve client availability, capability, accuracy, and learning efficiency, surpassing heuristic and tabular reinforcement learning solutions.

arXiv:2405.07004

Stealthy Imitation: Reward-guided Environment-free Policy Stealing

Deep reinforcement learning policies, which are integral to modern control systems, represent valuable intellectual property. The development of these policies demands considerable resources, such as domain expertise, simulation fidelity, and real-world validation. These policies are potentially vulnerable to model stealing attacks, which aim to replicate their functionality using only black-box access. In this paper, we propose Stealthy Imitation, the first attack designed to steal policies without access to the environment or knowledge of the input range. This setup has not been considered by previous model stealing methods. Lacking access to the victim's input states distribution, Stealthy Imitation fits a reward model that allows to approximate it. We show that the victim policy is harder to imitate when the distribution of the attack queries matches that of the victim. We evaluate our approach across diverse, high-dimensional control tasks and consistently outperform prior data-free approaches adapted for policy stealing. Lastly, we propose a countermeasure that significantly diminishes the effectiveness of the attack.

arXiv:2405.06774

Hedging American Put Options with Deep Reinforcement Learning

This article leverages deep reinforcement learning (DRL) to hedge American put options, utilizing the deep deterministic policy gradient (DDPG) method. The agents are first trained and tested with Geometric Brownian Motion (GBM) asset paths and demonstrate superior performance over traditional strategies like the Black-Scholes (BS) Delta, particularly in the presence of transaction costs. To assess the real-world applicability of DRL hedging, a second round of experiments uses a market calibrated stochastic volatility model to train DRL agents. Specifically, 80 put options across 8 symbols are collected, stochastic volatility model coefficients are calibrated for each symbol, and a DRL agent is trained for each of the 80 options by simulating paths of the respective calibrated model. Not only do DRL agents outperform the BS Delta method when testing is conducted using the same calibrated stochastic volatility model data from training, but DRL agents achieves better results when hedging the true asset path that occurred between the option sale date and the maturity. As such, not only does this study present the first DRL agents tailored for American put option hedging, but results on both simulated and empirical market testing data also suggest the optimality of DRL agents over the BS Delta method in real-world scenarios. Finally, note that this study employs a model-agnostic Chebyshev interpolation method to provide DRL agents with option prices at each time step when a stochastic volatility model is used, thereby providing a general framework for an easy extension to more complex underlying asset processes.

arXiv:2405.07087

Auditing an Automatic Grading Model with deep Reinforcement Learning

We explore the use of deep reinforcement learning to audit an automatic short answer grading (ASAG) model. Automatic grading may decrease the time burden of rating open-ended items for educators, but a lack of robust evaluation methods for these models can result in uncertainty of their quality. Current state-of-the-art ASAG models are configured to match human ratings from a training set, and researchers typically assess their quality with accuracy metrics that signify agreement between model and human scores. In this paper, we show that a high level of agreement to human ratings does not give sufficient evidence that an ASAG model is infallible. We train a reinforcement learning agent to revise student responses with the objective of achieving a high rating from an automatic grading model in the least number of revisions. By analyzing the agent's revised responses that achieve a high grade from the ASAG model but would not be considered a high scoring responses according to a scoring rubric, we discover ways in which the automated grader can be exploited, exposing shortcomings in the grading model.

arXiv:2405.07759

MADRL-Based Rate Adaptation for 360° Video Streaming with Multi-Viewpoint Prediction

Over the last few years, 360{\deg} video traffic on the network has grown significantly. A key challenge of 360{\deg} video playback is ensuring a high quality of experience (QoE) with limited network bandwidth. Currently, most studies focus on tile-based adaptive bitrate (ABR) streaming based on single viewport prediction to reduce bandwidth consumption. However, the performance of models for single-viewpoint prediction is severely limited by the inherent uncertainty in head movement, which can not cope with the sudden movement of users very well. This paper first presents a multimodal spatial-temporal attention transformer to generate multiple viewpoint trajectories with their probabilities given a historical trajectory. The proposed method models viewpoint prediction as a classification problem and uses attention mechanisms to capture the spatial and temporal characteristics of input video frames and viewpoint trajectories for multi-viewpoint prediction. After that, a multi-agent deep reinforcement learning (MADRL)-based ABR algorithm utilizing multi-viewpoint prediction for 360{\deg} video streaming is proposed for maximizing different QoE objectives under various network conditions. We formulate the ABR problem as a decentralized partially observable Markov decision process (Dec-POMDP) problem and present a MAPPO algorithm based on centralized training and decentralized execution (CTDE) framework to solve the problem. The experimental results show that our proposed method improves the defined QoE metric by up to 85.5% compared to existing ABR methods.

arXiv:2405.04218

Deep Reinforcement Learning for Multi-User RF Charging with Non-linear Energy Harvesters

Radio frequency (RF) wireless power transfer (WPT) is a promising technology for sustainable support of massive Internet of Things (IoT). However, RF-WPT systems are characterized by low efficiency due to channel attenuation, which can be mitigated by precoders that adjust the transmission directivity. This work considers a multi-antenna RF-WPT system with multiple non-linear energy harvesting (EH) nodes with energy demands changing over discrete time slots. This leads to the charging scheduling problem, which involves choosing the precoders at each slot to minimize the total energy consumption and meet the EH requirements. We model the problem as a Markov decision process and propose a solution relying on a low-complexity beamforming and deep deterministic policy gradient (DDPG). The results show that the proposed beamforming achieves near-optimal performance with low computational complexity, and the DDPG-based approach converges with the number of episodes and reduces the system's power consumption, while the outage probability and the power consumption increase with the number of devices.

arXiv:2405.04012

Latency and Energy Minimization in NOMA-Assisted MEC Network: A Federated Deep Reinforcement Learning Approach

Multi-access edge computing (MEC) is seen as a vital component of forthcoming 6G wireless networks, aiming to support emerging applications that demand high service reliability and low latency. However, ensuring the ultra-reliable and low-latency performance of MEC networks poses a significant challenge due to uncertainties associated with wireless links, constraints imposed by communication and computing resources, and the dynamic nature of network traffic. Enabling ultra-reliable and low-latency MEC mandates efficient load balancing jointly with resource allocation. In this paper, we investigate the joint optimization problem of offloading decisions, computation and communication resource allocation to minimize the expected weighted sum of delivery latency and energy consumption in a non-orthogonal multiple access (NOMA)-assisted MEC network. Given the formulated problem is a mixed-integer non-linear programming (MINLP), a new multi-agent federated deep reinforcement learning (FDRL) solution based on double deep Q-network (DDQN) is developed to efficiently optimize the offloading strategies across the MEC network while accelerating the learning process of the Internet-of-Thing (IoT) devices. Simulation results show that the proposed FDRL scheme can effectively reduce the weighted sum of delivery latency and energy consumption of IoT devices in the MEC network and outperform the baseline approaches.

arXiv:2405.04342공식 코드 · Papers with Code

The Curse of Diversity in Ensemble-Based Exploration

We uncover a surprising phenomenon in deep reinforcement learning: training a diverse ensemble of data-sharing agents -- a well-established exploration strategy -- can significantly impair the performance of the individual ensemble members when compared to standard single-agent training. Through careful analysis, we attribute the degradation in performance to the low proportion of self-generated data in the shared training data for each ensemble member, as well as the inefficiency of the individual ensemble members to learn from such highly off-policy data. We thus name this phenomenon the curse of diversity. We find that several intuitive solutions -- such as a larger replay buffer or a smaller ensemble size -- either fail to consistently mitigate the performance loss or undermine the advantages of ensembling. Finally, we demonstrate the potential of representation learning to counteract the curse of diversity with a novel method named Cross-Ensemble Representation Learning (CERL) in both discrete and continuous control domains. Our work offers valuable insights into an unexpected pitfall in ensemble-based exploration and raises important caveats for future applications of similar approaches.

arXiv:2405.03891

Enhancing O-RAN Security: Evasion Attacks and Robust Defenses for Graph Reinforcement Learning-based Connection Management

Adversarial machine learning, focused on studying various attacks and defenses on machine learning (ML) models, is rapidly gaining importance as ML is increasingly being adopted for optimizing wireless systems such as Open Radio Access Networks (O-RAN). A comprehensive modeling of the security threats and the demonstration of adversarial attacks and defenses on practical AI based O-RAN systems is still in its nascent stages. We begin by conducting threat modeling to pinpoint attack surfaces in O-RAN using an ML-based Connection management application (xApp) as an example. The xApp uses a Graph Neural Network trained using Deep Reinforcement Learning and achieves on average 54% improvement in the coverage rate measured as the 5th percentile user data rates. We then formulate and demonstrate evasion attacks that degrade the coverage rates by as much as 50% through injecting bounded noise at different threat surfaces including the open wireless medium itself. Crucially, we also compare and contrast the effectiveness of such attacks on the ML-based xApp and a non-ML based heuristic. We finally develop and demonstrate robust training-based defenses against the challenging physical/jamming-based attacks and show a 15% improvement in the coverage rates when compared to employing no defense over a range of noise budgets

arXiv:2405.03711

Guidance Design for Escape Flight Vehicle Using Evolution Strategy Enhanced Deep Reinforcement Learning

Guidance commands of flight vehicles are a series of data sets with fixed time intervals, thus guidance design constitutes a sequential decision problem and satisfies the basic conditions for using deep reinforcement learning (DRL). In this paper, we consider the scenario where the escape flight vehicle (EFV) generates guidance commands based on DRL and the pursuit flight vehicle (PFV) generates guidance commands based on the proportional navigation method. For the EFV, the objective of the guidance design entails progressively maximizing the residual velocity, subject to the constraint imposed by the given evasion distance. Thus an irregular dynamic max-min problem of extremely large-scale is formulated, where the time instant when the optimal solution can be attained is uncertain and the optimum solution depends on all the intermediate guidance commands generated before. For solving this problem, a two-step strategy is conceived. In the first step, we use the proximal policy optimization (PPO) algorithm to generate the guidance commands of the EFV. The results obtained by PPO in the global search space are coarse, despite the fact that the reward function, the neural network parameters and the learning rate are designed elaborately. Therefore, in the second step, we propose to invoke the evolution strategy (ES) based algorithm, which uses the result of PPO as the initial value, to further improve the quality of the solution by searching in the local space. Simulation results demonstrate that the proposed guidance design method based on the PPO algorithm is capable of achieving a residual velocity of 67.24 m/s, higher than the residual velocities achieved by the benchmark soft actor-critic and deep deterministic policy gradient algorithms. Furthermore, the proposed ES-enhanced PPO algorithm outperforms the PPO algorithm by 2.7\%, achieving a residual velocity of 69.04 m/s.

arXiv:2405.02299

Deep Reinforcement Learning for Modelling Protein Complexes

AlphaFold can be used for both single-chain and multi-chain protein structure prediction, while the latter becomes extremely challenging as the number of chains increases. In this work, by taking each chain as a node and assembly actions as edges, we show that an acyclic undirected connected graph can be used to predict the structure of multi-chain protein complexes (a.k.a., protein complex modelling, PCM). However, there are still two challenges: 1) The huge combinatorial optimization space of $N^{N-2}$ ($N$ is the number of chains) for the PCM problem can easily lead to high computational cost. 2) The scales of protein complexes exhibit distribution shift due to variance in chain numbers, which calls for the generalization in modelling complexes of various scales. To address these challenges, we propose GAPN, a Generative Adversarial Policy Network powered by domain-specific rewards and adversarial loss through policy gradient for automatic PCM prediction. Specifically, GAPN learns to efficiently search through the immense assembly space and optimize the direct docking reward through policy gradient. Importantly, we design an adversarial reward function to enhance the receptive field of our model. In this way, GAPN will simultaneously focus on a specific batch of complexes and the global assembly rules learned from complexes with varied chain numbers. Empirically, we have achieved both significant accuracy (measured by RMSD and TM-Score) and efficiency improvements compared to leading PCM softwares.

arXiv:2405.02676공식 코드 · Papers with Code

Hand-Object Interaction Controller (HOIC): Deep Reinforcement Learning for Reconstructing Interactions with Physics

Hand manipulating objects is an important interaction motion in our daily activities. We faithfully reconstruct this motion with a single RGBD camera by a novel deep reinforcement learning method to leverage physics. Firstly, we propose object compensation control which establishes direct object control to make the network training more stable. Meanwhile, by leveraging the compensation force and torque, we seamlessly upgrade the simple point contact model to a more physical-plausible surface contact model, further improving the reconstruction accuracy and physical correctness. Experiments indicate that without involving any heuristic physical rules, this work still successfully involves physics in the reconstruction of hand-object interactions which are complex motions hard to imitate with deep reinforcement learning. Our code and data are available at https://github.com/hu-hy17/HOIC.

arXiv:2405.02481공식 코드 · Papers with Code

Proximal Curriculum with Task Correlations for Deep Reinforcement Learning

Curriculum design for reinforcement learning (RL) can speed up an agent's learning process and help it learn to perform well on complex tasks. However, existing techniques typically require domain-specific hyperparameter tuning, involve expensive optimization procedures for task selection, or are suitable only for specific learning objectives. In this work, we consider curriculum design in contextual multi-task settings where the agent's final performance is measured w.r.t. a target distribution over complex tasks. We base our curriculum design on the Zone of Proximal Development concept, which has proven to be effective in accelerating the learning process of RL agents for uniform distribution over all tasks. We propose a novel curriculum, ProCuRL-Target, that effectively balances the need for selecting tasks that are not too difficult for the agent while progressing the agent's learning toward the target distribution via leveraging task correlations. We theoretically justify the task selection strategy of ProCuRL-Target by analyzing a simple learning setting with REINFORCE learner model. Our experimental results across various domains with challenging target task distributions affirm the effectiveness of our curriculum strategy over state-of-the-art baselines in accelerating the training process of deep RL agents.

arXiv:2405.02425

Learning Robot Soccer from Egocentric Vision with Deep Reinforcement Learning

We apply multi-agent deep reinforcement learning (RL) to train end-to-end robot soccer policies with fully onboard computation and sensing via egocentric RGB vision. This setting reflects many challenges of real-world robotics, including active perception, agile full-body control, and long-horizon planning in a dynamic, partially-observable, multi-agent domain. We rely on large-scale, simulation-based data generation to obtain complex behaviors from egocentric vision which can be successfully transferred to physical robots using low-cost sensors. To achieve adequate visual realism, our simulation combines rigid-body physics with learned, realistic rendering via multiple Neural Radiance Fields (NeRFs). We combine teacher-based multi-agent RL and cross-experiment data reuse to enable the discovery of sophisticated soccer strategies. We analyze active-perception behaviors including object tracking and ball seeking that emerge when simply optimizing perception-agnostic soccer play. The agents display equivalent levels of performance and agility as policies with access to privileged, ground-truth state. To our knowledge, this paper constitutes a first demonstration of end-to-end training for multi-agent robot soccer, mapping raw pixel observations to joint-level actions, that can be deployed in the real world. Videos of the game-play and analyses can be seen on our website https://sites.google.com/view/vision-soccer .

arXiv:2405.03262

End-to-End Reinforcement Learning of Curative Curtailment with Partial Measurement Availability

In the course of the energy transition, the expansion of generation and consumption will change, and many of these technologies, such as PV systems, electric cars and heat pumps, will influence the power flow, especially in the distribution grids. Scalable methods that can make decisions for each grid connection are needed to enable congestion-free grid operation in the distribution grids. This paper presents a novel end-to-end approach to resolving congestion in distribution grids with deep reinforcement learning. Our architecture learns to curtail power and set appropriate reactive power to determine a non-congested and, thus, feasible grid state. State-of-the-art methods such as the optimal power flow (OPF) demand high computational costs and detailed measurements of every bus in a grid. In contrast, the presented method enables decisions under sparse information with just some buses observable in the grid. Distribution grids are generally not yet fully digitized and observable, so this method can be used for decision-making on the majority of low-voltage grids. On a real low-voltage grid the approach resolves 100\% of violations in the voltage band and 98.8\% of asset overloads. The results show that decisions can also be made on real grids that guarantee sufficient quality for congestion-free grid operation.

arXiv:2405.03064공식 코드 · Papers with Code

RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation

Deep reinforcement learning (DRL) is playing an increasingly important role in real-world applications. However, obtaining an optimally performing DRL agent for complex tasks, especially with sparse rewards, remains a significant challenge. The training of a DRL agent can be often trapped in a bottleneck without further progress. In this paper, we propose RICE, an innovative refining scheme for reinforcement learning that incorporates explanation methods to break through the training bottlenecks. The high-level idea of RICE is to construct a new initial state distribution that combines both the default initial states and critical states identified through explanation methods, thereby encouraging the agent to explore from the mixed initial states. Through careful design, we can theoretically guarantee that our refining scheme has a tighter sub-optimality bound. We evaluate RICE in various popular RL environments and real-world applications. The results demonstrate that RICE significantly outperforms existing refining schemes in enhancing agent performance.

arXiv:2405.02754

Implicit Safe Set Algorithm for Provably Safe Reinforcement Learning

Deep reinforcement learning (DRL) has demonstrated remarkable performance in many continuous control tasks. However, a significant obstacle to the real-world application of DRL is the lack of safety guarantees. Although DRL agents can satisfy system safety in expectation through reward shaping, designing agents to consistently meet hard constraints (e.g., safety specifications) at every time step remains a formidable challenge. In contrast, existing work in the field of safe control provides guarantees on persistent satisfaction of hard safety constraints. However, these methods require explicit analytical system dynamics models to synthesize safe control, which are typically inaccessible in DRL settings. In this paper, we present a model-free safe control algorithm, the implicit safe set algorithm, for synthesizing safeguards for DRL agents that ensure provable safety throughout training. The proposed algorithm synthesizes a safety index (barrier certificate) and a subsequent safe control law solely by querying a black-box dynamic function (e.g., a digital twin simulator). Moreover, we theoretically prove that the implicit safe set algorithm guarantees finite time convergence to the safe set and forward invariance for both continuous-time and discrete-time systems. We validate the proposed algorithm on the state-of-the-art Safety Gym benchmark, where it achieves zero safety violations while gaining $95\% \pm 9\%$ cumulative reward compared to state-of-the-art safe DRL methods. Furthermore, the resulting algorithm scales well to high-dimensional systems with parallel computing.

arXiv:2405.01604

Portfolio Management using Deep Reinforcement Learning

Algorithmic trading or Financial robots have been conquering the stock markets with their ability to fathom complex statistical trading strategies. But with the recent development of deep learning technologies, these strategies are becoming impotent. The DQN and A2C models have previously outperformed eminent humans in game-playing and robotics. In our work, we propose a reinforced portfolio manager offering assistance in the allocation of weights to assets. The environment proffers the manager the freedom to go long and even short on the assets. The weight allocation advisements are restricted to the choice of portfolio assets and tested empirically to knock benchmark indices. The manager performs financial transactions in a postulated liquid market without any transaction charges. This work provides the conclusion that the proposed portfolio manager with actions centered on weight allocations can surpass the risk-adjusted returns of conventional portfolio managers.

arXiv:2405.01616

Generative Active Learning for the Search of Small-molecule Protein Binders

Despite substantial progress in machine learning for scientific discovery in recent years, truly de novo design of small molecules which exhibit a property of interest remains a significant challenge. We introduce LambdaZero, a generative active learning approach to search for synthesizable molecules. Powered by deep reinforcement learning, LambdaZero learns to search over the vast space of molecules to discover candidates with a desired property. We apply LambdaZero with molecular docking to design novel small molecules that inhibit the enzyme soluble Epoxide Hydrolase 2 (sEH), while enforcing constraints on synthesizability and drug-likeliness. LambdaZero provides an exponential speedup in terms of the number of calls to the expensive molecular docking oracle, and LambdaZero de novo designed molecules reach docking scores that would otherwise require the virtual screening of a hundred billion molecules. Importantly, LambdaZero discovers novel scaffolds of synthesizable, drug-like inhibitors for sEH. In in vitro experimental validation, a series of ligands from a generated quinazoline-based scaffold were synthesized, and the lead inhibitor N-(4,6-di(pyrrolidin-1-yl)quinazolin-2-yl)-N-methylbenzamide (UM0152893) displayed sub-micromolar enzyme inhibition of sEH.

arXiv:2405.01284

Behavior Imitation for Manipulator Control and Grasping with Deep Reinforcement Learning

The existing Motion Imitation models typically require expert data obtained through MoCap devices, but the vast amount of training data needed is difficult to acquire, necessitating substantial investments of financial resources, manpower, and time. This project combines 3D human pose estimation with reinforcement learning, proposing a novel model that simplifies Motion Imitation into a prediction problem of joint angle values in reinforcement learning. This significantly reduces the reliance on vast amounts of training data, enabling the agent to learn an imitation policy from just a few seconds of video and exhibit strong generalization capabilities. It can quickly apply the learned policy to imitate human arm motions in unfamiliar videos. The model first extracts skeletal motions of human arms from a given video using 3D human pose estimation. These extracted arm motions are then morphologically retargeted onto a robotic manipulator. Subsequently, the retargeted motions are used to generate reference motions. Finally, these reference motions are used to formulate a reinforcement learning problem, enabling the agent to learn a policy for imitating human arm motions. This project excels at imitation tasks and demonstrates robust transferability, accurately imitating human arm motions from other unfamiliar videos. This project provides a lightweight, convenient, efficient, and accurate Motion Imitation model. While simplifying the complex process of Motion Imitation, it achieves notably outstanding performance.