اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدPrediction-Free, Real-Time Flexible Control of Tidal Lagoons through Proximal Policy Optimisation: A Case Study for the Swansea Lagoon
122
0
0.0
(
0
)
نشر من قبل
T\\'ulio Marcondes Moreira
تاريخ النشر
2021
مجال البحث
الهندسة المعلوماتية
والبحث باللغة
English
تأليف
Tulio Marcondes Moreira
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Tidal range structures have been considered for large scale electricity generation for their potential ability to produce reasonable predictable energy without the emission of greenhouse gases. Once the main forcing components for driving the tides have deterministic dynamics, the available energy in a given tidal power plant has been estimated, through analytical and numerical optimisation routines, as a mostly predictable event. This constraint imposes state-of-art flexible operation methods to rely on tidal predictions (concurrent with measured data and up to a multiple of half-tidal cycles into the future) to infer best operational strategies for tidal lagoons, with the additional cost of requiring to run optimisation routines for every new tide. In this paper, we propose a novel optimised operation of tidal lagoons with proximal policy optimisation through Unity ML-Agents. We compare this technique with 6 different operation optimisation approaches (baselines) devised from the literature, utilising the Swansea Bay Tidal Lagoon as a case study. We show that our approach is successful in maximising energy generation through an optimised operational policy of turbines and sluices, yielding competitive results with state-of-the-art methods of optimisation, regardless of test data used, requiring training once and performing real-time flexible control with measured ocean data only.
قيم البحث
اقرأ أيضاً
We present Luce, the first life-long predictive model for automated property valuation. Luce addresses two critical issues of property valuation: the lack of recent sold prices and the sparsity of house data. It is designed to operate on a limited vo
lume of recent house transaction data. As a departure from prior work, Luce organizes the house data in a heterogeneous information network (HIN) where graph nodes are house entities and attributes that are important for house price valuation. We employ a Graph Convolutional Network (GCN) to extract the spatial information from the HIN for house-related data like geographical locations, and then use a Long Short Term Memory (LSTM) network to model the temporal dependencies for house transaction data over time. Unlike prior work, Luce can make effective use of the limited house transactions data in the past few months to update valuation information for all house entities within the HIN. By providing a complete and up-to-date house valuation dataset, Luce thus massively simplifies the downstream valuation task for the targeting properties. We demonstrate the benefit of Luce by applying it to large, real-life datasets obtained from the Toronto real estate market. Extensive experimental results show that Luce not only significantly outperforms prior property valuation methods but also often reaches and sometimes exceeds the valuation accuracy given by independent experts when using the actual realization price as the ground truth.
We introduce a new algorithm for reinforcement learning called Maximum aposteriori Policy Optimisation (MPO) based on coordinate ascent on a relative entropy objective. We show that several existing methods can directly be related to our derivation.
We develop two off-policy algorithms and demonstrate that they are competitive with the state-of-the-art in deep reinforcement learning. In particular, for continuous control, our method outperforms existing methods with respect to sample efficiency, premature convergence and robustness to hyperparameter settings while achieving similar or better final performance.
This paper introduces two simple techniques to improve off-policy Reinforcement Learning (RL) algorithms. First, we formulate off-policy RL as a stochastic proximal point iteration. The target network plays the role of the variable of optimization an
d the value network computes the proximal operator. Second, we exploits the two value functions commonly employed in state-of-the-art off-policy algorithms to provide an improved action value estimate through bootstrapping with limited increase of computational resources. Further, we demonstrate significant performance improvement over state-of-the-art algorithms on standard continuous-control RL benchmarks.
Credit assignment in Meta-reinforcement learning (Meta-RL) is still poorly understood. Existing methods either neglect credit assignment to pre-adaptation behavior or implement it naively. This leads to poor sample-efficiency during meta-training as
well as ineffective task identification strategies. This paper provides a theoretical analysis of credit assignment in gradient-based Meta-RL. Building on the gained insights we develop a novel meta-learning algorithm that overcomes both the issue of poor credit assignment and previous difficulties in estimating meta-policy gradients. By controlling the statistical distance of both pre-adaptation and adapted policies during meta-policy search, the proposed algorithm endows efficient and stable meta-learning. Our approach leads to superior pre-adaptation policy behavior and consistently outperforms previous Meta-RL algorithms in sample-efficiency, wall-clock time, and asymptotic performance.
We introduce a methodology for efficiently computing a lower bound to empowerment, allowing it to be used as an unsupervised cost function for policy learning in real-time control. Empowerment, being the channel capacity between actions and states, m
aximises the influence of an agent on its near future. It has been shown to be a good model of biological behaviour in the absence of an extrinsic goal. But empowerment is also prohibitively hard to compute, especially in nonlinear continuous spaces. We introduce an efficient, amortised method for learning empowerment-maximising policies. We demonstrate that our algorithm can reliably handle continuous dynamical systems using system dynamics learned from raw data. The resulting policies consistently drive the agents into states where they can use their full potential.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
