Filters








17,085 Hits in 4.5 sec

Autonomous Reinforcement Learning: Formalism and Benchmarking [article]

Archit Sharma, Kelvin Xu, Nikhil Sardana, Abhishek Gupta, Karol Hausman, Sergey Levine, Chelsea Finn
2022 arXiv   pre-print
In this paper, we aim to address this discrepancy by laying out a framework for Autonomous Reinforcement Learning (ARL): reinforcement learning where the agent not only learns through its own experience  ...  Reinforcement learning (RL) provides a naturalistic framing for learning through trial and error, which is appealing both because of its simplicity and effectiveness and because of its resemblance to how  ...  We also thank the IRIS and RAIL members for their feedback on the work at various stages.  ... 
arXiv:2112.09605v2 fatcat:e5yh2ngaxbaldabrsxmxhtudiu

Autonomous robotic nanofabrication with reinforcement learning [article]

Philipp Leinen, Malte Esders, Kristof T. Schütt, Christian Wagner, Klaus-Robert Müller, F. Stefan Tautz
2020 arXiv   pre-print
Our approach employs reinforcement learning (RL), which is able to learn solution strategies even in the face of large uncertainty and with sparse feedback.  ...  Here, we present a strategy to work around both obstacles, and demonstrate autonomous robotic nanofabrication by manipulating single molecules.  ...  Acknowledgements The authors acknowledge support from the Institute for Pure and Applied Mathematics (IPAM) at UCLA (pro-  ... 
arXiv:2002.11952v1 fatcat:hxvyz4jannboxdvjrk7tmken7u

Autonomous Reinforcement Learning via Subgoal Curricula [article]

Archit Sharma, Abhishek Gupta, Sergey Levine, Karol Hausman, Chelsea Finn
2021 arXiv   pre-print
Reinforcement learning (RL) promises to enable autonomous acquisition of complex behaviors for diverse agents.  ...  autonomous acquisition of complex behaviors.  ...  Persistent Reinforcement Learning In this section, we formalize the persistent reinforcement learning as an optimization problem.  ... 
arXiv:2107.12931v2 fatcat:r57cjeaxinaehbnxi5uousob2q

Autonomous robotic nanofabrication with reinforcement learning

Philipp Leinen, Malte Esders, Kristof T. Schütt, Christian Wagner, Klaus-Robert Müller, F. Stefan Tautz
2020 Science Advances  
Our approach uses reinforcement learning (RL), which finds solution strategies even in the face of large uncertainty and sparse feedback.  ...  Here, we present a strategy to work around both obstacles and demonstrate autonomous robotic nanofabrication by manipulating single molecules.  ...  This leaves autonomous robotic nanofabrication as the preferred option. In the current study, we show that reinforcement learning (RL) can be used to automate a manipulation task at the nanoscale.  ... 
doi:10.1126/sciadv.abb6987 pmid:32917594 fatcat:gankonbwbjac7n5qdjsl7uhzha

Autonomous Quadrotor Landing using Deep Reinforcement Learning [article]

Riccardo Polvara, Massimiliano Patacchiola, Sanjay Sharma, Jian Wan, Andrew Manning, Robert Sutton, Angelo Cangelosi
2018 arXiv   pre-print
In this article, we propose a method based on deep reinforcement learning that only requires low-resolution images taken from a down-looking camera in order to identify the position of the marker and land  ...  We implemented different technical solutions, such as the combination of vanilla and double DQNs, and a partitioned buffer replay.  ...  PROPOSED METHOD In this section we describe the landing problem in reinforcement learning terms and we present the technical solutions we adopted. A.  ... 
arXiv:1709.03339v3 fatcat:rbeduw5kuvaafeei3lm3wixt2e

Dependability Analysis of Deep Reinforcement Learning based Robotics and Autonomous Systems through Probabilistic Model Checking [article]

Yi Dong, Xingyu Zhao, Xiaowei Huang
2022 arXiv   pre-print
While Deep Reinforcement Learning (DRL) provides transformational capabilities to the control of Robotics and Autonomous Systems (RAS), the black-box nature of DRL and uncertain deployment environments  ...  In this paper, we formally define a set of dependability properties in temporal logic and construct a Discrete-Time Markov Chain (DTMC) to model the dynamics of risk/failures of a DRL-driven RAS interacting  ...  Based on traditional software systems, Zhu et al. developed the formal verification technology for reinforcement learning verification [28] .  ... 
arXiv:2109.06523v3 fatcat:tfkizgpwjbfefmtuerjoam75ge

A Versatile and Efficient Reinforcement Learning Framework for Autonomous Driving [article]

Guan Wang, Haoyi Niu, Desheng Zhu, Jianming Hu, Xianyuan Zhan, Guyue Zhou
2022 arXiv   pre-print
In this study, we propose a versatile and efficient reinforcement learning framework and build a fully functional autonomous vehicle for real-world validation.  ...  As a way of marrying the advantages of both approaches, learning a semantically meaningful representation and then use in the downstream driving policy learning tasks provides a viable and attractive solution  ...  Imitation Learning VS Reinforcement Learning In end-to-end framework, IL [2]- [8] has been identified as a practical paradigm for autonomous driving.  ... 
arXiv:2110.11573v2 fatcat:fhjv37a6i5apxgghwe6ve27arm

Adversarial Reinforcement Learning Framework for Benchmarking Collision Avoidance Mechanisms in Autonomous Vehicles [article]

Vahid Behzadan, Arslan Munir
2018 arXiv   pre-print
This work proposes a novel framework based on deep reinforcement learning for benchmarking the behavior of collision avoidance mechanisms under the worst-case scenario of dealing with an optimal adversarial  ...  With the rapidly growing interest in autonomous navigation, the body of research on motion planning and collision avoidance techniques has enjoyed an accelerating rate of novel proposals and developments  ...  adversarial deep reinforcement learning to measure the reliability of motion planning and collision avoidance mechanisms in autonomous vehicles.  ... 
arXiv:1806.01368v1 fatcat:pitfzjr2prbulfkw6b4fs2a66y

An Autonomous Negotiating Agent Framework with Reinforcement Learning Based Strategies and Adaptive Strategy Switching Mechanism [article]

Ayan Sengupta, Yasser Mohammad, Shinji Nakadai
2021 arXiv   pre-print
We demonstrate an instance of our framework by implementing maximum entropy reinforcement learning based strategies with a deep learning based opponent classifier.  ...  This work focuses on both, solving the problem of expert selection and adapting to the opponent's behaviour with our Autonomous Negotiating Agent Framework.  ...  Then again, in the last couple of decades several studies have looked at the application of reinforcement learning (RL) algorithms like Q-learning [17, 20, 46, 48, 49] and REINFORCE [47] in automated  ... 
arXiv:2102.03588v2 fatcat:c67dxtxzdzfdbgsdrnwbkvwig4

Autonomous Highway Driving using Deep Reinforcement Learning [article]

Subramanya Nageshrao, Eric Tseng, Dimitar Filev
2019 arXiv   pre-print
In order to address these issues and to avoid peculiar behaviors when encountering unforeseen scenario, we propose a reinforcement learning (RL) based method, where the ego car, i.e., an autonomous vehicle  ...  To best address the issue, this paper incorporates reinforcement learning with an additional short horizon safety check (SC).  ...  Reinforcement learning In reinforcement learning (RL) an agent learns an optimal behavior with respect to a cost function by directly interacting with the system.  ... 
arXiv:1904.00035v1 fatcat:f3l2cjkya5eapddkgrhruknisi

An Investigation of Reinforcement Learning for Reactive Search Optimization [chapter]

Roberto Battiti, Paolo Campigotto
2011 Autonomous Search  
This work studies reinforcement learning methods for the online tuning of parameters in stochastic local search algorithms.  ...  The proposed framework is applied for tuning the prohibition value in the Reactive Tabu Search, the noise parameter in the Adaptive Walksat, and the smoothing probability in the Reactive Scaling and Probabilistic  ...  Reinforcement learning and dynamic programming basics In this section, Markov decision processes are formally defined and the standard dynamic programming technique is summarized in Sec. 3.2, while the  ... 
doi:10.1007/978-3-642-21434-9_6 fatcat:loeyms4zrffzhlsf2x4btykhiy

Efficient Deep Reinforcement Learning with Imitative Expert Priors for Autonomous Driving [article]

Zhiyu Huang, Jingda Wu, Chen Lv
2021 arXiv   pre-print
Deep reinforcement learning (DRL) is a promising way to achieve human-like autonomous driving.  ...  Our framework consists of three ingredients, namely expert demonstration, policy derivation, and reinforcement learning.  ...  Imitation learning and reinforcement learning Imitation learning (IL) and reinforcement learning (RL) are two promising tools to be applied in autonomous driving, which can help develop adaptive, flexible  ... 
arXiv:2103.10690v3 fatcat:2ykxfzdjgne7vpn6hph3koe6di

Autonomous Taxi Driving Environment Using Reinforcement Learning Algorithms

Showkat A. Dar, Department of Computer Science and Engineering, Annamalai University, India, S. Palanivel, M. Kalaiselvi Geetha
2022 International Journal of Modern Education and Computer Science  
RL (Reinforcement Learning) has evolved into a robust learning model which can learn about complications in high dimensional settings, owing to the advent of deep representation learning.  ...  autonomously.  ...  [32] proposed a NDRL (New Adversarial Deep Reinforcement Learning) method for improving the robustness of ATD dynamics when adversaries try to inject erroneous data into sensor readings of autonomous  ... 
doi:10.5815/ijmecs.2022.03.06 fatcat:sjbawudl5ncytkhhj3erbc6vuq

Driver Dojo: A Benchmark for Generalizable Reinforcement Learning for Autonomous Driving [article]

Sebastian Rietsch, Shih-Yuan Huang, Georgios Kontes, Axel Plinge, Christopher Mutschler
2022 arXiv   pre-print
Reinforcement learning (RL) has shown to reach super human-level performance across a wide range of tasks.  ...  Autonomous driving (AD) provides a multi-faceted experimental field, as it is necessary to learn the correct behavior over many variations of road layouts and large distributions of possible traffic situations  ...  Acknowledgements This work was supported by the Bavarian Ministry for Economic Affairs, Infrastructure, Transport and Technology through the Center for Analytics-Data-Applications (ADA-Center) within the  ... 
arXiv:2207.11432v1 fatcat:6m2aqnsxljbi5g56cb5yf4gvre

Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning [article]

Benjamin Eysenbach, Shixiang Gu, Julian Ibarz, Sergey Levine
2017 arXiv   pre-print
In this work, we propose an autonomous method for safe and efficient reinforcement learning that simultaneously learns a forward and reset policy, with the reset policy resetting the environment for a  ...  Deep reinforcement learning algorithms can learn complex behavioral skills, but real-world application of these methods requires a large amount of experience to be collected by the agent.  ...  Acknowledgements: We thank Sergio Guadarrama, Oscar Ramirez, and Anoop Korattikara for implementing DDPG and thank Peter Pastor for insightful discussions.  ... 
arXiv:1711.06782v1 fatcat:g7apzaaf5zbz3dcjzlehifpyde
« Previous Showing results 1 — 15 out of 17,085 results