اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدZero-Shot Adaptation for mmWave Beam-Tracking on Overhead Messenger Wires through Robust Adversarial Reinforcement Learning
49
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Millimeter wave (mmWave) beam-tracking based on machine learning enables the development of accurate tracking policies while obviating the need to periodically solve beam-optimization problems. However, its applicability is still arguable when training-test gaps exist in terms of environmental parameters that affect the node dynamics. From this skeptical point of view, the contribution of this study is twofold. First, by considering an example scenario, we confirm that the training-test gap adversely affects the beam-tracking performance. More specifically, we consider nodes placed on overhead messenger wires, where the node dynamics are affected by several environmental parameters, e.g, the wire mass and tension. Although these are particular scenarios, they yield insight into the validation of the training-test gap problems. Second, we demonstrate the feasibility of textit{zero-shot adaptation} as a solution, where a learning agent adapts to environmental parameters unseen during training. This is achieved by leveraging a robust adversarial reinforcement learning (RARL) technique, where such training-and-test gaps are regarded as disturbances by adversaries that are jointly trained with a legitimate beam-tracking agent. Numerical evaluations demonstrate that the beam-tracking policy learned via RARL can be applied to a wide range of environmental parameters without severely degrading the received power.
قيم البحث
اقرأ أيضاً
This paper discusses the feasibility of beam tracking against dynamics in millimeter wave (mmWave) nodes placed on overhead messenger wires, including wind-forced perturbations and disturbances caused by impulsive forces to wires. Our main contributi
on is to answer whether or not historical positions and velocities of a mmWave node is useful to track directional beams given the complicated on-wire dynamics. To this end, we implement beam-tracking based on deep reinforcement learning (DRL) to learn the complicated relationships between the historical positions/velocities and appropriate beam steering angles. Our numerical evaluations yielded the following key insights: Against wind perturbations, an appropriate beam-tracking policy can be learned from the historical positions and velocities of a node. Meanwhile, against impulsive forces to the wire, the use of the position and velocity of the node is not necessarily sufficient owing to the rapid displacement of the node. To solve this, we propose to take advantage of the positional interaction on the wire by leveraging the positions/velocities of several points on the wire as state information in DRL. The results confirmed that this results in the avoidance of beam misalignment, which would not be possible by using only the position/velocity of the node.
Deep neural networks, including reinforcement learning agents, have been proven vulnerable to small adversarial changes in the input, thus making deploying such networks in the real world problematic. In this paper, we propose RADIAL-RL, a method to
train reinforcement learning agents with improved robustness against any $l_p$-bounded adversarial attack. By simply minimizing an upper bound of the loss functions under worst case adversarial perturbation derived from efficient robustness verification methods, we significantly improve robustness of RL-agents trained on Atari-2600 games and show that RADIAL-RL can beat state-of-the-art robust training algorithms when evaluated against PGD-attacks. We also propose a new evaluation method, Greedy Worst-Case Reward (GWC), for measuring attack agnostic robustness of RL agents. GWC can be evaluated efficiently and it serves as a good estimate of the reward under the worst possible sequence of adversarial attacks; in particular, GWC accounts for the importance of each action and their temporal dependency, improving upon previous approaches that only evaluate whether each single action can change under input perturbations. Our code is available at https://github.com/tuomaso/radial_rl.
Although deep reinforcement learning (deep RL) methods have lots of strengths that are favorable if applied to autonomous driving, real deep RL applications in autonomous driving have been slowed down by the modeling gap between the source (training)
domain and the target (deployment) domain. Unlike current policy transfer approaches, which generally limit to the usage of uninterpretable neural network representations as the transferred features, we propose to transfer concrete kinematic quantities in autonomous driving. The proposed robust-control-based (RC) generic transfer architecture, which we call RL-RC, incorporates a transferable hierarchical RL trajectory planner and a robust tracking controller based on disturbance observer (DOB). The deep RL policies trained with known nominal dynamics model are transfered directly to the target domain, DOB-based robust tracking control is applied to tackle the modeling gap including the vehicle dynamics errors and the external disturbances such as side forces. We provide simulations validating the capability of the proposed method to achieve zero-shot transfer across multiple driving scenarios such as lane keeping, lane changing and obstacle avoidance.
Reinforcement Learning (RL) is an effective tool for controller design but can struggle with issues of robustness, failing catastrophically when the underlying system dynamics are perturbed. The Robust RL formulation tackles this by adding worst-case
adversarial noise to the dynamics and constructing the noise distribution as the solution to a zero-sum minimax game. However, existing work on learning solutions to the Robust RL formulation has primarily focused on training a single RL agent against a single adversary. In this work, we demonstrate that using a single adversary does not consistently yield robustness to dynamics variations under standard parametrizations of the adversary; the resulting policy is highly exploitable by new adversaries. We propose a population-based augmentation to the Robust RL formulation in which we randomly initialize a population of adversaries and sample from the population uniformly during training. We empirically validate across robotics benchmarks that the use of an adversarial population results in a more robust policy that also improves out-of-distribution generalization. Finally, we demonstrate that this approach provides comparable robustness and generalization as domain randomization on these benchmarks while avoiding a ubiquitous domain randomization failure mode.
We introduce a new RL problem where the agent is required to generalize to a previously-unseen environment characterized by a subtask graph which describes a set of subtasks and their dependencies. Unlike existing hierarchical multitask RL approaches
that explicitly describe what the agent should do at a high level, our problem only describes properties of subtasks and relationships among them, which requires the agent to perform complex reasoning to find the optimal subtask to execute. To solve this problem, we propose a neural subtask graph solver (NSGS) which encodes the subtask graph using a recursive neural network embedding. To overcome the difficulty of training, we propose a novel non-parametric gradient-based policy, graph reward propagation, to pre-train our NSGS agent and further finetune it through actor-critic method. The experimental results on two 2D visual domains show that our agent can perform complex reasoning to find a near-optimal way of executing the subtask graph and generalize well to the unseen subtask graphs. In addition, we compare our agent with a Monte-Carlo tree search (MCTS) method showing that our method is much more efficient than MCTS, and the performance of NSGS can be further improved by combining it with MCTS.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
