Deep reinforcement learning for improving competitive cycling performance
نویسندگان
چکیده
Developing expert systems that make use of artificial intelligence (AI) to provide predictive analytics as well targeted recommendations for decision support has been gaining momentum in recent years. Both academia and industry are looking into creating such solve real-world problems tackle specific challenges. In our work, we investigate the potential application different machine learning approaches solutions around competitive cycling. Specifically, build evaluate prediction models capable accurately predicting a cyclist’s speed heart rate using sensory information collected during bike rides. addition, create recommendation module is able real-time action suggestions cyclists regarding their posture with goal improving overall performance. We achieve this combination model-based reinforcement (RL) deep RL. particular, RL learn “simulator” rides profiles extracted from sensors placed on cyclists’ back. then Q-learning simulator extract policies improve behavior ride. Our evaluation shows by recommending actions throughout ride, can increase average only minimal impact rate. The results presented paper constitute clear evidence advanced AI techniques prime candidate further developing intelligent cycling other similar areas.
منابع مشابه
Deep Reinforcement Learning for Improving Downlink mmWave Communication Performance
We propose a method to improve the DL SINR for a single cell indoor base station operating in the millimeter wave frequency range using deep reinforcement learning. In this paper, we use the deep-Q reinforcement learning models to arrive at optimal sequences of actions to improve the cellular network SINR value from a starting to a feasible target value. While deep reinforcement learning has be...
متن کاملOn Improving Deep Reinforcement Learning for POMDPs
Deep Reinforcement Learning (RL) recently emerged as one of the most competitive approaches for learning in sequential decision making problems with fully observable environments, e.g., computer Go. However, very little work has been done in deep RL to handle partially observable environments. We propose a new architecture called Action-specific Deep Recurrent Q-Network (ADRQN) to enhance learn...
متن کاملImproving Elevator Performance Using Reinforcement Learning
This paper describes the application of reinforcement learning (RL) to the di cult real world problem of elevator dispatching. The elevator domain poses a combination of challenges not seen in most RL research to date. Elevator systems operate in continuous state spaces and in continuous time as discrete event dynamic systems. Their states are not fully observable and they are nonstationary due...
متن کاملDeep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning
Deep artificial neural networks (DNNs) are typically trained via gradient-based learning algorithms, namely backpropagation. Evolution strategies (ES) can rival backprop-based algorithms such as Q-learning and policy gradients on challenging deep reinforcement learning (RL) problems. However, ES can be considered a gradient-based algorithm because it performs stochastic gradient descent via an ...
متن کاملDeep Reinforcement Learning for 2048
In this paper, we explore the performance of a Reinforcement Learning algorithm using a Policy Neural Network to play the popular game 2048. After proposing a modelization of the state and action spaces, we review our learning process, and train a first model without incorporating any prior knwoledge of the game. We prove that a simple Probabilistic Policy Network achieves a 4 times higher maxi...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Expert Systems With Applications
سال: 2022
ISSN: ['1873-6793', '0957-4174']
DOI: https://doi.org/10.1016/j.eswa.2022.117311