A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
RLlib: Abstractions for Distributed Reinforcement Learning
[article]
2018
arXiv
pre-print
Preserved Fulltext
Other Versions
Reinforcement learning (RL) algorithms involve the deep nesting of highly irregular computation patterns, each of which typically exhibits opportunities for distributed computation. ...
We demonstrate the benefits of this principle through RLlib: a library that provides scalable software primitives for RL. ...
Abstractions for Reinforcement Learning To leverage RLlib for distributed execution, algorithms must declare their policy π, experience postprocessor ρ, and loss L. ...
arXiv:1712.09381v4
fatcat:ihhwdewi4bfndags5x5c65mfaa
RLlib Flow: Distributed Reinforcement Learning is a Dataflow Problem
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
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 ...
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. ...
In contrast to supervised learning, it is more difficult to provide a fixed set of abstractions for scaling RL training. ...
arXiv:2011.12719v4
fatcat:o7euvwohgrgtrazko3niasln4e
MALib: A Parallel Framework for Population-based Multi-agent Reinforcement Learning
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Population-based multi-agent reinforcement learning (PB-MARL) refers to the series of methods nested with reinforcement learning (RL) algorithms, which produces a self-generated sequence of tasks arising ...
both training and sampling, and meets the evaluation requirement of auto-curriculum learning; (3) a higher-level abstraction of MARL training paradigms, which enables efficient code reuse and flexible ...
Yi Qu for her help on the design work. ...
arXiv:2106.07551v1
fatcat:xrdy7ppkbbfd3ogjjci3ace4wi
RL: Generic reinforcement learning codebase in TensorFlow
2019
Journal of Open Source Software
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Vast reinforcement learning (RL) research groups, such as DeepMind and OpenAI, have their internal (private) reinforcement learning codebases, which enable quick prototyping and comparing of ideas to many ...
Currently, there does not exist any RL codebase, to the author's knowledge, which contains all the five properties, particularly with TensorBoard logging and abstracting away cloud hardware such as TPU's ...
Acknowledgements We would like to thank all other members of For.ai, for useful discussions and feedback. ...
doi:10.21105/joss.01524
fatcat:5jnp7brex5aydi2aswx2lcpvyu
Motion Planning by Reinforcement Learning for an Unmanned Aerial Vehicle in Virtual Open Space with Static Obstacles
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this study, we applied reinforcement learning based on the proximal policy optimization algorithm to perform motion planning for an unmanned aerial vehicle (UAV) in an open space with static obstacles ...
As the reinforcement learning progressed, the mean reward and goal rate of the model were increased. ...
We used RLlib [30] to perform reinforcement learning in the Gym environment. ...
arXiv:2009.11799v1
fatcat:mi7vrghiyfeztexefbuqcl7uhu
RLgraph: Modular Computation Graphs for Deep Reinforcement Learning
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
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. ...
Further, we thank Lasse Espeholt for providing support to replicate IMPALA results. We also want to thank the RLlib authors for helping to replicate Ape-X results. ...
arXiv:1810.09028v2
fatcat:7q4mc2z4njdsnmrnfrriqqkfw4
PowerGridworld: A Framework for Multi-Agent Reinforcement Learning in Power Systems
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
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 can be deployed on both cloud and high performance computing (HPC) systems, and it provides a number of training "abstractions," enabling users to develop custom, distributed RL algorithms. ...
arXiv:2111.05969v1
fatcat:jisj34ccbnaghldi2oiobllfk4
Mava: a research framework for distributed multi-agent reinforcement learning
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Breakthrough advances in reinforcement learning (RL) research have led to a surge in the development and application of RL. ...
Mava provides useful components, abstractions, utilities and tools for MARL and allows for simple scaling for multi-process system training and execution, while providing a high level of flexibility and ...
In this work, we present Mava, a research framework for distributed multi-agent reinforcement learning. ...
arXiv:2107.01460v1
fatcat:nuymlvbeendtpe3thy77qqp4ba
Learning to Fly – a Gym Environment with PyBullet Physics for Reinforcement Learning of Multi-agent Quadcopter Control
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Vice versa, many reinforcement learning environments trade-off realism for high sample throughputs in toy-like problems. ...
We demonstrate its use through several examples, either for control (trajectory tracking with PID control, multi-robot flight with downwash, etc.) or reinforcement learning (single and multi-agent stabilization ...
We also thank the Vector Institute for providing access to its computing resources. ...
arXiv:2103.02142v3
fatcat:vzgoqo2sxja7tgjv3oc4o4bqoy
Running Alchemist on Cray XC and CS Series Supercomputers: Dask and PySpark Interfaces, Deployment Options, and Data Transfer Times
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
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. ...
matrix using the [VC, STAR] layout and a 100MB buffer is used for the messages, which is Alchemist's default setting. ...
arXiv:1910.01354v2
fatcat:5ho4jp775fc2rftmyk5phpwivi
Bellman: A Toolbox for Model-Based Reinforcement Learning in TensorFlow
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2021 pre-print arXiv:2103.14407v1 fatcat:mzh53iwcsfamxm4o33wudnbciy
In the past decade, model-free reinforcement learning (RL) has provided solutions to challenging domains such as robotics. ...
This demonstrates the necessity for a toolbox to push the boundaries for model-based RL. ...
RLlib: Abstractions for distributed reinforcement learning. ...
arXiv:2103.14407v2
fatcat:c7mzfbm7w5g4vapexxzj4p66li
SURREAL-System: Fully-Integrated Stack for Distributed Deep Reinforcement Learning
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
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. ...
We propose SURREAL-SYSTEM, a reproducible, flexible, and scalable framework for distributed reinforcement learning. 2. ...
arXiv:1909.12989v2
fatcat:l7w77vhs4nfu7fjhw3hdn5iksy
Verified Probabilistic Policies for Deep Reinforcement Learning
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Deep reinforcement learning is an increasingly popular technique for synthesising policies to control an agent's interaction with its environment. ...
In this paper, we tackle the problem of verifying probabilistic policies for deep reinforcement learning, which are used to, for example, tackle adversarial environments, break symmetries and manage trade-offs ...
Conclusion We presented an approach for verifying probabilistic policies for deep reinforcement learning agents. ...
arXiv:2201.03698v1
fatcat:6q6tle2d45aphn6gicqci7h5f4
Wield: Systematic Reinforcement Learning With Progressive Randomization
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Reinforcement learning frameworks have introduced abstractions to implement and execute algorithms at scale. ...
We present Wield, a first-of-its kind system to facilitate task design for practical reinforcement learning. ...
We are also grateful for receiving research credits from Google Cloud. ...
arXiv:1909.06844v1
fatcat:hsaisvqntzex7ihfxzmhhmfalm
Catalyst.RL: A Distributed Framework for Reproducible RL Research
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
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 ...
Main features of our library include large-scale asynchronous distributed training, easy-to-use configuration files with the complete list of hyperparameters for the particular experiments, efficient implementations ...
., 2018] presented Dopamine 5 , a research framework for fast prototyping of reinforcement learning algorithms in TensorFlow. ...
arXiv:1903.00027v1
fatcat:4sdbs2r4f5hsxoe4kok4kpvpdi
« Previous
Showing results 1 — 15 out of 89 results