Filters








87 Hits in 6.9 sec

rl_reach: Reproducible Reinforcement Learning Experiments for Robotic Reaching Tasks [article]

Pierre Aumjaud, David McAuliffe, Francisco Javier Rodríguez Lera, Philip Cardiff
2021 arXiv   pre-print
We present rl_reach, a self-contained, open-source and easy-to-use software package designed to run reproducible reinforcement learning experiments for customisable robotic reaching tasks. rl_reach packs  ...  Training reinforcement learning agents at solving a given task is highly dependent on identifying optimal sets of hyperparameters and selecting suitable environment input / output configurations.  ...  Acknowledgements This Career-FIT project has received funding from the European Union's Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No. 713654.  ... 
arXiv:2102.04916v1 fatcat:nsm3resrlnfnllu25aufdclrcy

rl_reach: Reproducible reinforcement learning experiments for robotic reaching tasks

Pierre Aumjaud, David McAuliffe, Francisco J. Rodriguez-Lera, Philip Cardiff
2021 Software Impacts  
Acknowledgements This Career-FIT project has received funding from the European Union's Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No. 713654.  ...  Reinforcement Learning (RL) is a general framework for solving sequential decision-making tasks through self-learning and as such, it has found natural applications in robotics.  ...  Finally, rl_reach provides learning environments designed to train a robotic manipulator to reach a target position.  ... 
doi:10.1016/j.simpa.2021.100061 fatcat:gxfzu56trjg5lhd5o7iemjckne

dm_control: Software and tasks for continuous control

Saran Tunyasuvunakool, Alistair Muldal, Yotam Doron, Siqi Liu, Steven Bohez, Josh Merel, Tom Erez, Timothy Lillicrap, Nicolas Heess, Yuval Tassa
2020 Software Impacts  
Manipulation We also provide examples of constructing robotic manipulation tasks. These tasks involve grabbing and manipulating objects with a 3D robotic arm.  ...  Introduction Reinforcement Learning (RL) casts sequential decision problems as interactions between an agent, which receives observations and outputs actions, and an environment, which receives actions  ... 
doi:10.1016/j.simpa.2020.100022 fatcat:n7whzjgxdbeyzfxybq3omqmuia

A survey of benchmarks for reinforcement learning algorithms

Belinda Stapelberg, Katherine Mary Malan
2020 South African Computer Journal  
This paper provides an overview of different contributions to reinforcement learning benchmarking and discusses how they can assist researchers to address the challenges facing reinforcement learning.  ...  \par The survey aims to bring attention to the wide range of reinforcement learning benchmarking tasks available and to encourage research to take place in a standardised manner.  ...  A research team from Stanford has introduced the open-source framework SURREAL (Scalable Robotic REinforcementlearning ALgorithms) and the SURREAL Robotics Suite (Fan et al., 2018) , to facilitate research  ... 
doi:10.18489/sacj.v32i2.746 fatcat:66fd47ejfbg6jcfykelm42klr4

A survey of benchmarking frameworks for reinforcement learning [article]

Belinda Stapelberg, Katherine M. Malan
2020 arXiv   pre-print
This paper provides an overview of different contributions to reinforcement learning benchmarking and discusses how they can assist researchers to address the challenges facing reinforcement learning.  ...  The survey aims to bring attention to the wide range of reinforcement learning benchmarking tasks available and to encourage research to take place in a standardised manner.  ...  A research team from Stanford has introduced the open-source framework SURREAL (Scalable Robotic REinforcementlearning ALgorithms) and the SURREAL Robotics Suite [89] , to facilitae research in RL in  ... 
arXiv:2011.13577v1 fatcat:uxjtrzl3erb4hk2xcbi6s6zqyq

robo-gym – An Open Source Toolkit for Distributed Deep Reinforcement Learning on Real and Simulated Robots [article]

Matteo Lucchi, Friedemann Zindler, Stephan Mühlbacher-Karrer, Horst Pichler
2020 arXiv   pre-print
In order to increase the use of DRL with real robots and reduce the gap between simulation and real world robotics, we propose an open source toolkit: robo-gym.  ...  Applying Deep Reinforcement Learning (DRL) to complex tasks in the field of robotics has proven to be very successful in the recent years.  ...  ACKNOWLEDGMENTS This research has received funding from the Austrian Ministry for Transport, Innovation and Technology (bmvit) within the project "Credible & Safe Robot Systems (Cre-dRoS)", from the "Kärntner  ... 
arXiv:2007.02753v2 fatcat:a5lvnmnivffqnoizvubu436y3a

Assistive Gym: A Physics Simulation Framework for Assistive Robotics [article]

Zackory Erickson, Vamsee Gangaram, Ariel Kapusta, C. Karen Liu, and Charles C. Kemp
2019 arXiv   pre-print
In this paper, we present Assistive Gym, an open source physics simulation framework for assistive robots that models multiple tasks.  ...  We present baseline policies trained using reinforcement learning for four different commercial robots in the six environments.  ...  This work was supported by NSF award IIS-1514258 and AWS Cloud Credits for Research. Dr. Kemp owns equity in and works for Hello Robot, a company commercializing robotic assistance technologies.  ... 
arXiv:1910.04700v1 fatcat:746mgtgwtrdqplt746bctmqdzi

DoorGym: A Scalable Door Opening Environment And Baseline Agent [article]

Yusuke Urakami, Alec Hodgkinson, Casey Carlin, Randall Leu, Luca Rigazio, Pieter Abbeel
2020 arXiv   pre-print
We introduce DoorGym, an open-source door opening simulation framework designed to utilize domain randomization to train a stable policy.  ...  Reinforcement Learning (RL) with Domain Randomization (DR) is a promising technique to enforce policy generalization, however, there are only a few accessible training environments that are inherently  ...  The SURREAL framework provides a straightforward framework with practical robotic manipulation tasks, but it is not designed to transfer policies between environments.  ... 
arXiv:1908.01887v3 fatcat:24q2f7n4rraplor4vpjlgwczgy

Guided Imitation of Task and Motion Planning [article]

Michael James McDonald, Dylan Hadfield-Menell
2021 arXiv   pre-print
Among these tasks, we can learn a policy that solves the RoboSuite 4-object pick-place task 88% of the time from object pose observations and a policy that solves the RoboDesk 9-goal benchmark 79% of the  ...  In robotic manipulation tasks with 7-DoF joint control, the partially trained policies reduce the time needed for planning by a factor of up to 2.6.  ...  Savarese, and L. Fei-Fei. Surreal: Open-source reinforcement learning framework and robot manipulation benchmark. In Conference on Robot Learning, 2018. [36] A. Mandlekar, F. Ramos, B.  ... 
arXiv:2112.03386v1 fatcat:liiwhjl67fao7phu2tuj4bj7yy

DeepRacer: Educational Autonomous Racing Platform for Experimentation with Sim2Real Reinforcement Learning [article]

Bharathan Balaji, Sunil Mallya, Sahika Genc, Saurabh Gupta, Leo Dirac, Vineet Khare, Gourav Roy, Tao Sun, Yunzhe Tao, Brian Townsend, Eddie Calleja, Sunil Muralidhara, Dhanasekar Karuppasamy
2019 arXiv   pre-print
We open source our code and video demo on GitHub: https://git.io/fjxoJ.  ...  It is the first successful large-scale deployment of deep reinforcement learning on a robotic control agent that uses only raw camera images as observations and a model-free learning method to perform  ...  INTRODUCTION Reinforcement Learning (RL) has been used to accomplish diverse robotic tasks: manipulation [1] , [2] , [3] , [4] , locomotion [5] , [6] , navigation [7] , [8] , [9] , [10] , flight  ... 
arXiv:1911.01562v1 fatcat:hknpe3mutfgvji4ljq23ygwmki

RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitation [article]

Ajay Mandlekar, Yuke Zhu, Animesh Garg, Jonathan Booher, Max Spero, Albert Tung, Julian Gao, John Emmons, Anchit Gupta, Emre Orbay, Silvio Savarese, Li Fei-Fei
2018 arXiv   pre-print
Imitation Learning has empowered recent advances in learning robotic manipulation tasks by addressing shortcomings of Reinforcement Learning such as exploration and reward specification.  ...  We show that the data obtained through RoboTurk enables policy learning on multi-step manipulation tasks with sparse rewards and that using larger quantities of demonstrations during policy learning provides  ...  We would also like to thank members of the Stanford People, AI & Robots (PAIR) group (pair.stanford.edu) and the anonymous reviewers for their constructive feedback.  ... 
arXiv:1811.02790v1 fatcat:qrtkjsf6ivewdeenq4d3fb2f6m

Continual Learning: Tackling Catastrophic Forgetting in Deep Neural Networks with Replay Processes [article]

Timothée Lesort
2020 arXiv   pre-print
We demonstrate their ability to learn continually through unsupervised learning, supervised learning and reinforcement learning tasks.  ...  Therefore, artificial neural networks are often inept to deal with real-life settings such as an autonomous-robot that has to learn on-line to adapt to new situations and overcome new problems without  ...  segmentation). • Reinforcement Learning: Arcade Learning Environment (ALE) Bellemare et al. (2013) for Atari games, SURREAL Fan et al. (2018) for robot manipulation and RoboTurk for robotic skill learning  ... 
arXiv:2007.00487v3 fatcat:fwdjynkclbchvgo73qhs6biice

Visual Navigation Among Humans With Optimal Control As A Supervisor

Varun Tolani, Somil Bansal, Aleksandra Faust, Claire Tomlin
2021 IEEE Robotics and Automation Letters  
Through simulations and experiments on a mobile robot, we demonstrate that the learned navigation policies can anticipate and react to humans without explicitly predicting future human motion, generalize  ...  Videos describing our approach and experiments, as well as a demo of HumANav are available on the project website. 1 Index Terms-Machine learning for robot control, transfer learning, vision-based navigation  ...  However, this comes at a tradeoff in the agility of the robot, causing it to get stuck in tight corners and narrow openings.  ... 
doi:10.1109/lra.2021.3060638 fatcat:fs2ajatw75fhzf73hzkunc62ru

Visual Navigation Among Humans with Optimal Control as a Supervisor [article]

Varun Tolani, Somil Bansal, Aleksandra Faust, Claire Tomlin
2021 arXiv   pre-print
Through simulations and experiments on a mobile robot, we demonstrate that the learned navigation policies can anticipate and react to humans without explicitly predicting future human motion, generalize  ...  Real world visual navigation requires robots to operate in unfamiliar, human-occupied dynamic environments.  ...  However, this comes at a tradeoff in the agility of the robot, causing it to get stuck in tight corners and narrow openings.  ... 
arXiv:2003.09354v2 fatcat:f22p6zaz7fbk7cmn6pxvachbdy

Deep Reinforcement Learning, a textbook [article]

Aske Plaat
2022 arXiv   pre-print
Deep reinforcement learning has gathered much attention recently. Impressive results were achieved in activities as diverse as autonomous driving, game playing, molecular recombination, and robotics.  ...  Developments go quickly, and we also cover advanced topics: deep multi-agent reinforcement learning, deep hierarchical reinforcement learning, and deep meta learning.  ...  Go and scored wins against Fuego, a strong open source Go program [227] based on MCTS without deep learning.  ... 
arXiv:2201.02135v2 fatcat:3icsopexerfzxa3eblpu5oal64
« Previous Showing results 1 — 15 out of 87 results