26 Hits in 2.5 sec

RLlib: Abstractions for Distributed Reinforcement Learning [article]

Eric Liang, Richard Liaw, Philipp Moritz, Robert Nishihara, Roy Fox, Ken Goldberg, Joseph E. Gonzalez, Michael I. Jordan, Ion Stoica
2018 arXiv   pre-print
We demonstrate the benefits of this principle through RLlib: a library that provides scalable software primitives for RL.  ...  These primitives enable a broad range of algorithms to be implemented with high performance, scalability, and substantial code reuse. RLlib is available at  ...  , CapitalOne, Ericsson, Facebook, Google, Huawei, Intel, Microsoft, Scotiabank, Splunk and VMware.  ... 
arXiv:1712.09381v4 fatcat:ihhwdewi4bfndags5x5c65mfaa

RLlib Flow: Distributed Reinforcement Learning is a Dataflow Problem [article]

Eric Liang, Zhanghao Wu, Michael Luo, Sven Mika, Joseph E. Gonzalez, Ion Stoica
2021 arXiv   pre-print
Researchers and practitioners in the field of reinforcement learning (RL) frequently leverage parallel computation, which has led to a plethora of new algorithms and systems in the last few years.  ...  We propose RLlib Flow, a hybrid actor-dataflow programming model for distributed RL, and validate its practicality by porting the full suite of algorithms in RLlib, a widely adopted distributed RL library  ...  Implementation We implemented RLlib Flow on the Ray distributed actor framework [24] as two separate modules: a general purpose parallel iterator library (1241 lines of code), and a collection of RL  ... 
arXiv:2011.12719v4 fatcat:o7euvwohgrgtrazko3niasln4e

PowerGridworld: A Framework for Multi-Agent Reinforcement Learning in Power Systems [article]

David Biagioni, Xiangyu Zhang, Dylan Wald, Deepthi Vaidhynathan, Rohit Chintala, Jennifer King, Ahmed S. Zamzam
2021 arXiv   pre-print
with existing training frameworks for reinforcement learning (RL).  ...  To highlight PowerGridworld's key features, we present two case studies and demonstrate learning MARL policies using both OpenAI's multi-agent deep deterministic policy gradient (MADDPG) and RLLib's proximal  ...  RLLib [16] , [17] is a framework for scalable RL training built on the Ray Python library [18] , and it supports a variety of training paradigms for single-agent, multi-agent, hierarchical, and offline  ... 
arXiv:2111.05969v1 fatcat:jisj34ccbnaghldi2oiobllfk4

RLgraph: Modular Computation Graphs for Deep Reinforcement Learning [article]

Michael Schaarschmidt, Sven Mika, Kai Fricke, Eiko Yoneki
2019 arXiv   pre-print
To this end, we introduce RLgraph, a library for designing and executing reinforcement learning tasks in both static graph and define-by-run paradigms.  ...  Reinforcement learning (RL) tasks are challenging to implement, execute and test due to algorithmic instability, hyper-parameter sensitivity, and heterogeneous distributed communication patterns.  ...  This research was supported by the EPSRC (grant references EP/M508007/1 and EP/P004024), the Alan Turing Institute, and a Sansom scholarship.  ... 
arXiv:1810.09028v2 fatcat:7q4mc2z4njdsnmrnfrriqqkfw4

skrl: Modular and Flexible Library for Reinforcement Learning [article]

Antonio Serrano-Muñoz, Nestor Arana-Arexolaleiba, Dimitrios Chrysostomou, Simon Bøgh
2022 arXiv   pre-print
skrl is an open-source modular library for reinforcement learning written in Python and designed with a focus on readability, simplicity, and transparency of algorithm implementations.  ...  The library's documentation can be found at and its source code is available on GitHub at url  ...  Acknowledgements -We would like to express our gratitude for the funding and support received from NVIDIA under a collaboration agreement with the Mondragon Unibertsitatea.  ... 
arXiv:2202.03825v1 fatcat:vmp4loml4nh5viyew3nvk4wfri

SURREAL-System: Fully-Integrated Stack for Distributed Deep Reinforcement Learning [article]

Linxi Fan, Yuke Zhu, Jiren Zhu, Zihua Liu, Orien Zeng, Anchit Gupta, Joan Creus-Costa, Silvio Savarese, Li Fei-Fei
2019 arXiv   pre-print
We present an overview of SURREAL-System, a reproducible, flexible, and scalable framework for distributed reinforcement learning (RL).  ...  The learning performances of our distributed algorithms establish new state-of-the-art on OpenAI Gym and Robotics Suites tasks.  ...  Acknowledgements We would like to thank many members of the Stanford People, AI & Robots (PAIR) group in using SURREAL in their research and providing insightful feedback.  ... 
arXiv:1909.12989v2 fatcat:l7w77vhs4nfu7fjhw3hdn5iksy

Mava: a research framework for distributed multi-agent reinforcement learning [article]

Arnu Pretorius, Kale-ab Tessera, Andries P. Smit, Claude Formanek, St John Grimbly, Kevin Eloff, Siphelele Danisa, Lawrence Francis, Jonathan Shock, Herman Kamper, Willie Brink, Herman Engelbrecht (+2 others)
2021 arXiv   pre-print
Breakthrough advances in reinforcement learning (RL) research have led to a surge in the development and application of RL.  ...  composability.  ...  RLLib (Liang et al., 2018) and Arena (Song et al., 2020) are libraries that support both single and multi-agent RL and is built on top of Ray (Moritz et al., 2017) for distributed training.  ... 
arXiv:2107.01460v1 fatcat:nuymlvbeendtpe3thy77qqp4ba

Running Alchemist on Cray XC and CS Series Supercomputers: Dask and PySpark Interfaces, Deployment Options, and Data Transfer Times [article]

Kai Rothauge, Haripriya Ayyalasomayajula, Kristyn J. Maschhoff, Michael Ringenburg, Michael W. Mahoney
2019 arXiv   pre-print
We also briefly discuss the combination of Alchemist with RLlib, an increasingly popular library for reinforcement learning, and consider the benefits of leveraging HPC simulations in reinforcement learning  ...  Alchemist is a system that allows Apache Spark to achieve better performance by interfacing with HPC libraries for large-scale distributed computations.  ...  In contrast, a [STAR, VC] layout requires the data in rows to be sent across columns that may be stored on different nodes by the DistMatrix, resulting in significantly more messages with less data and  ... 
arXiv:1910.01354v2 fatcat:5ho4jp775fc2rftmyk5phpwivi

PyTorchRL: Modular and Distributed Reinforcement Learning in PyTorch [article]

Albert Bou, Gianni De Fabritiis
2021 arXiv   pre-print
To this end, we present PyTorchRL, a PyTorch-based library for RL with a modular design that allows composing agents from a set of reusable and easily extendable modules.  ...  Deep reinforcement learning (RL) has proved successful at solving challenging environments but often requires scaling to large sampling and computing resources.  ...  Libraries such as PyTorchRL, RLlib (Liang et al., 2017) and RLgraph (Schaarschmidt et al., 2019) use Ray to obtain highly efficient distributed reinforcement learning implementations, with logically  ... 
arXiv:2007.02622v2 fatcat:6kvqjw2qjba6lbuk57ahpq4ida

Catalyst.RL: A Distributed Framework for Reproducible RL Research [article]

Sergey Kolesnikov, Oleksii Hrinchuk
2019 arXiv   pre-print
Despite the recent progress in deep reinforcement learning field (RL), and, arguably because of it, a large body of work remains to be done in reproducing and carefully comparing different RL algorithms  ...  model with a prosthetic leg to walk and run.  ...  ., 2018] introduced RLLib 4 , an open-source library for RL that offered both a collection of reference algorithms and scalable primitives for composing new ones.  ... 
arXiv:1903.00027v1 fatcat:4sdbs2r4f5hsxoe4kok4kpvpdi

CompilerGym: Robust, Performant Compiler Optimization Environments for AI Research [article]

Chris Cummins, Bram Wasti, Jiadong Guo, Brandon Cui, Jason Ansel, Sahir Gomez, Somya Jain, Jia Liu, Olivier Teytaud, Benoit Steiner, Yuandong Tian, Hugh Leather
2021 arXiv   pre-print
Unlike in other domains, compiler and AI researchers do not have access to the datasets and frameworks that enable fast iteration and development of ideas, and getting started requires a significant engineering  ...  We introduce CompilerGym, a set of environments for real world compiler optimization tasks, and a toolkit for exposing new optimization tasks to compiler researchers.  ...  These wrappers can be composed. Listing 2 shows integration with the popular RLlib [9] library using two of these wrappers. D.  ... 
arXiv:2109.08267v2 fatcat:s2a3qrrk7zczflszoeta3ztl7q

Learning Mobile Manipulation through Deep Reinforcement Learning

Cong Wang, Qifeng Zhang, Qiyan Tian, Shuo Li, Xiaohui Wang, David Lane, Yvan Petillot, Sen Wang
2020 Sensors  
A novel mobile manipulation system which integrates the state-of-the-art deep reinforcement learning algorithms with visual perception is proposed.  ...  However, it is usually more challenging than fixed-base manipulation due to the complex coordination of a mobile base and a manipulator.  ...  Acknowledgments: We would like to thank the anonymous reviewers and academic editor for their comments and suggestions.  ... 
doi:10.3390/s20030939 pmid:32050678 pmcid:PMC7039391 fatcat:yg3pdjoosrathioxsg3hbywp44

OpenGraphGym-MG: Using Reinforcement Learning to Solve Large Graph Optimization Problems on MultiGPU Systems [article]

Weijian Zheng, Dali Wang, Fengguang Song
2021 arXiv   pre-print
This paper presents an extensible, high performance framework (named OpenGraphGym-MG) that uses deep reinforcement learning and graph embedding to solve large graph optimization problems with multiple  ...  This study performs a comprehensive performance analysis on parallel efficiency and memory cost that proves the parallel RL training and inference algorithms are efficient and highly scalable on a number  ...  Ray RLlib: A composable and scalable reinforcement learning library.  ... 
arXiv:2105.08764v2 fatcat:r6ejpsl4srdizgh6vld5cffnum

AI-driven Prices for Sustainable Production Markets [article]

Panayiotis Danassis, Aris Filos-Ratsikas, Boi Faltings
2022 arXiv   pre-print
We propose a practical approach to computing market prices and allocations via a deep reinforcement learning policymaker agent, operating in an environment of other learning agents.  ...  Our policymaker allows us to tune the prices with regard to diverse objectives such as sustainability and resource wastefulness, fairness, buyers' and sellers' welfare, etc.  ...  RLlib ( is an open-source library on top of Ray ( for Multi-Agent Deep Reinforcement Learning (Liang et al., 2017) .13  ... 
arXiv:2106.06060v2 fatcat:e2b2nwpavnf3dauu6lf5vn7kdq

Parallel Actors and Learners: A Framework for Generating Scalable RL Implementations [article]

Chi Zhang, Sanmukh Rao Kuppannagari, Viktor K Prasanna
2021 arXiv   pre-print
In this work, we propose a framework for generating scalable reinforcement learning implementations on multi-core systems.  ...  Our framework supports a wide range of reinforcement learning algorithms including DQN, DDPG, etc.  ...  RLlib [25] proposes abstractions for distributed reinforcement learning for software developers built on top of the Ray library [25] written in Python [23] .  ... 
arXiv:2110.01101v2 fatcat:l75h3vpewjf5bdyzpnbevsbigm
« Previous Showing results 1 — 15 out of 26 results