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
Deep Model-Based Reinforcement Learning for High-Dimensional Problems, a Survey
[article]
2020
arXiv
pre-print
Preserved Fulltext
Other Versions
Model-based reinforcement learning creates an explicit model of the environment dynamics to reduce the need for environment samples. ...
In recent years, many model-based methods have been introduced to address this challenge. In this paper, we survey the contemporary model-based landscape. ...
ACKNOWLEDGMENTS We thank the members of the Leiden Reinforcement Learning Group, and especially Thomas Moerland and Mike Huisman, for many discussions and insights. ...
arXiv:2008.05598v2
fatcat:5xmwmemv5bfinkw57avf5ghhxq
A survey of benchmarks for reinforcement learning algorithms
2020
South African Computer Journal
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.
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. ...
Reinforcement learning has recently experienced increased prominence in the machine learning community. ...
and model-based reinforcement learning approaches There are different aspects of RL systems that can be learnt. ...
doi:10.18489/sacj.v32i2.746
fatcat:66fd47ejfbg6jcfykelm42klr4
Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning
[article]
2017
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
In this work, we demonstrate that medium-sized neural network models can in fact be combined with model predictive control (MPC) to achieve excellent sample complexity in a model-based reinforcement learning ...
Model-free deep reinforcement learning algorithms have been shown to be capable of learning a wide range of robotic skills, but typically require a very large number of samples to achieve good performance ...
MODEL-BASED DEEP REINFORCEMENT LEARNING We now present our model-based deep reinforcement learning algorithm. We detail our learned dynamics function f θ (s t , a t ) in Sec. ...
arXiv:1708.02596v2
fatcat:zfjugkxaabcm7mjc7qw4oboxse
Overcoming Model Bias for Robust Offline Deep 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.
Other Versions
To improve robustness and stability of the learning process, we use dynamics models to assess policy performance instead of value functions, resulting in MOOSE (MOdel-based Offline policy Search with Ensembles ...
State-of-the-art reinforcement learning algorithms mostly rely on being allowed to directly interact with their environment to collect millions of observations. ...
Acknowledgements The project this paper is based on was supported with funds from the German Federal Ministry of Education and Research under project number 01 IS 18049 A. ...
arXiv:2008.05533v4
fatcat:r2dw73ki7jdklarbxtsjvxdd2e
A survey of benchmarking frameworks for reinforcement learning
[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.
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. ...
Model-free and model-based reinforcement learning approaches There are different aspects of RL systems that can be learnt. ...
arXiv:2011.13577v1
fatcat:uxjtrzl3erb4hk2xcbi6s6zqyq
CURL: Contrastive Unsupervised Representations for Reinforcement Learning
[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.
Other Versions
We present CURL: Contrastive Unsupervised Representations for Reinforcement Learning. ...
CURL outperforms prior pixel-based methods, both model-based and model-free, on complex tasks in the DeepMind Control Suite and Atari Games showing 1.9x and 1.2x performance gains at the 100K environment ...
We benchmark extensively against both model-based and model-free algorithms in our experiments. ...
arXiv:2004.04136v4
fatcat:fek5n6xsn5f23efn2anivekvde
Baconian: A Unified Open-source Framework for Model-Based 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.
Other Versions
Model-Based Reinforcement Learning (MBRL) is one category of Reinforcement Learning (RL) algorithms which can improve sampling efficiency by modeling and approximating system dynamics. ...
INTRODUCTION Model-Based Reinforcement Learning (MBRL) is proposed to reduce sample complexity introduced by model-free Deep Reinforcement Learning (DRL) algorithms [12] . ...
Since many model-based algorithms are built upon model-free algorithms, we also implement some popular model-free algorithms including DQN [7] , DDPG [11] , and PPO [14] in Baconian. ...
arXiv:1904.10762v4
fatcat:cs2i4eubzfbbfmdudwttrxdh4u
Google Research Football: A Novel Reinforcement Learning Environment
2020
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
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.
We introduce the Google Research Football Environment, a new reinforcement learning environment where agents are trained to play football in an advanced, physics-based 3D simulator. ...
Recent progress in the field of reinforcement learning has been accelerated by virtual learning environments such as video games, where novel algorithms and ideas can be quickly tested in a safe and reproducible ...
We expect that these benchmark tasks will be useful for investigating current scientific challenges in reinforcement learning such as sampleefficiency, sparse rewards, or model-based approaches. ...
doi:10.1609/aaai.v34i04.5878
fatcat:b2tov7kieza3fajhsxavfni5qm
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. ...
benchmarks that share characteristics with real-world problems. ...
Benchmarking model-based reinforcement learning. arXiv, 2019. URL https: //github.com/WilsonWangTHU/mbbl. Y Wu, E Mansimov, S Liao, R Grosse, and J Ba. ...
arXiv:2103.14407v2
fatcat:c7mzfbm7w5g4vapexxzj4p66li
High-Accuracy Model-Based Reinforcement Learning, a Survey
[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.
To reduce the number of environment samples, model-based reinforcement learning creates an explicit model of the environment dynamics. ...
Deep reinforcement learning has shown remarkable success in the past few years. ...
Acknowledgments We thank the members of the Leiden Reinforcement Learning Group, and especially Thomas Moerland and Mike Huisman, for many discussions and insights. ...
arXiv:2107.08241v1
fatcat:tma6xb2uy5fybjfhmzasfx2cta
A2CM: a new multi-agent algorithm
2021
ACTA IMEKO
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.
One subcategory of reinforcement learning is multi-agent reinforcement learning, in which multiple agents are present in the world. ...
<p class="Abstract">Reinforcement learning is currently one of the most researched fields of artificial intelligence. ...
Apart from the aforementioned model-free reinforcement learning methods, there is also model-based reinforcement learning. ...
doi:10.21014/acta_imeko.v10i3.1023
fatcat:fiasvepa3rc7np4vhfwljp5bfq
HOList: An Environment for Machine Learning of Higher-Order Theorem Proving
[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 provide an open-source framework based on the HOL Light theorem prover that can be used as a reinforcement learning environment. ...
We also present a deep reinforcement learning driven automated theorem prover, DeepHOL, with strong initial results on this benchmark. ...
This paper provides a benchmark and reinforcement learning environment for theorem proving. ...
arXiv:1904.03241v3
fatcat:ih4fizuonrbvzk2oyu4pekhftu
Google Research Football: A Novel Reinforcement Learning Environment
[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.
Other Versions
We introduce the Google Research Football Environment, a new reinforcement learning environment where agents are trained to play football in an advanced, physics-based 3D simulator. ...
Recent progress in the field of reinforcement learning has been accelerated by virtual learning environments such as video games, where novel algorithms and ideas can be quickly tested in a safe and reproducible ...
We expect that these benchmark tasks will be useful for investigating current scientific challenges in reinforcement learning such as sampleefficiency, sparse rewards, or model-based approaches. ...
arXiv:1907.11180v2
fatcat:3iwdl6e5cnfnvnpupwy6fz552y
ReLeTA: Reinforcement Learning for Thermal-Aware Task Allocation on Multicore
[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.
In this paper, we propose ReLeTA: Reinforcement Learning based Task Allocation for temperature minimization. ...
We design a new reward function and use a new state model to facilitate optimization of reinforcement learning algorithm. ...
Reinforcement Learning Environment Agent State Reward Action S t S t R t R t A t A t
Fig. 1: Reinforcement learning Different from the widely used supervised learning algorithms which learn a prediction ...
arXiv:1912.00189v1
fatcat:3em4azgvmzhrxpbexojffmvyie
safe-control-gym: a Unified Benchmark Suite for Safe Learning-based Control and 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.
Other Versions
Here, we propose a new open-source benchmark suite, called safe-control-gym, supporting both model-based and data-based control techniques. ...
control, and reinforcement learning. ...
reinforcement learning [4] . ...
arXiv:2109.06325v3
fatcat:q7dpbgtog5aqlgocuom2kdbwvq
« Previous
Showing results 1 — 15 out of 89,308 results