Filters








116,275 Hits in 3.1 sec

Efficient Competitive Self-Play Policy Optimization [article]

Yuanyi Zhong, Yuan Zhou, Jian Peng
<span title="2020-09-13">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we propose a new algorithmic framework for competitive self-play reinforcement learning in two-player zero-sum games.  ...  Self-play, where the agents compete with themselves, is often used to generate training data for iterative policy improvement.  ...  Conclusion We propose a new algorithmic framework for competitive self-play policy optimization inspired by a perturbation subgradient method for saddle points.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.06086v1">arXiv:2009.06086v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/f2aoh452wraxhmnbsydvhodd2a">fatcat:f2aoh452wraxhmnbsydvhodd2a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201118232623/https://arxiv.org/pdf/2009.06086v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/25/2b/252b1f4f3bfbffe8400f1cfd3a2a95d932e959e0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.06086v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Page 395 of Sage Public Administration Abstracts Vol. 26, Issue 3 [page]

<span title="">1999</span> <i title="Sage Publications, Inc"> <a target="_blank" rel="noopener" href="https://archive.org/details/pub_sage-public-administration-abstracts" style="color: black;">Sage Public Administration Abstracts </a> </i> &nbsp;
The study is able to show that, even if firms play dynamic games among themselves, it is possible to construct tax rules that achieve efficiency.  ...  As stressed by the traditional public-choice approach to economics, economic policy, including environmental policy, is determined by political and economic self-interest.  ... 
<span class="external-identifiers"> </span>
<a target="_blank" rel="noopener" href="https://archive.org/details/sim_sage-public-administration-abstracts_1999-10_26_3/page/395" title="read fulltext microfilm" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Archive [Microfilm] <div class="menu fulltext-thumbnail"> <img src="https://archive.org/serve/sim_sage-public-administration-abstracts_1999-10_26_3/__ia_thumb.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a>

JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning [article]

Zichuan Lin, Junyou Li, Jianing Shi, Deheng Ye, Qiang Fu, Wei Yang
<span title="2021-12-07">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
learning for efficient exploration, and 3) ensemble behavior cloning with consistency filtering for policy robustness.  ...  Notably, we won the championship of the NeurIPS MineRL 2021 research competition and achieved the highest performance score ever.  ...  and encourages the development of sample-efficient RL agents for playing Minecraft.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.04907v1">arXiv:2112.04907v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/sz4tps5w25a37mrdfjvcaaqe6y">fatcat:sz4tps5w25a37mrdfjvcaaqe6y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211212001720/https://arxiv.org/pdf/2112.04907v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/51/51/51517d5d900a7c0cd33e210c48cb27ef3b96e5a9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.04907v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Provable Self-Play Algorithms for Competitive Reinforcement Learning [article]

Yu Bai, Chi Jin
<span title="2020-07-09">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To the best of our knowledge, our work presents the first line of provably sample-efficient self-play algorithms for competitive reinforcement learning.  ...  We study self-play in competitive reinforcement learning under the setting of Markov games, a generalization of Markov decision processes to the two-player case.  ...  These self-play algorithms are able to learn a good policy for all players from scratch through repeatedly playing the current policies against each other and performing policy updates using these self-played  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.04017v3">arXiv:2002.04017v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/r36v54jlfrho7jsgdfrsjqx3zq">fatcat:r36v54jlfrho7jsgdfrsjqx3zq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200910052231/https://arxiv.org/pdf/2002.04017v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/53/2a/532a8221a8a2d38941e80f0661a479c4fd3671e9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.04017v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Competitive Experience Replay [article]

Hao Liu, Alexander Trott, Richard Socher, Caiming Xiong
<span title="2019-02-17">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
However, in sparse reward environment it still often suffers from the need to carefully shape reward function to guide policy optimization.  ...  We propose a novel method called competitive experience replay, which efficiently supplements a sparse reward by placing learning in the context of an exploration competition between a pair of agents.  ...  Our method is partly inspired by the success of self-play in learning to play competitive games, where sparse rewards (i.e. win or lose) are common.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1902.00528v4">arXiv:1902.00528v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pxqopbrljzeltabolip6ticriy">fatcat:pxqopbrljzeltabolip6ticriy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200825195711/https://arxiv.org/pdf/1902.00528v4.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/08/b2/08b2cf3b10fa771af300c8b7408fd9457b3d08e0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1902.00528v4" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Modular Architecture for StarCraft II with Deep Reinforcement Learning [article]

Dennis Lee, Haoran Tang, Jeffrey O Zhang, Huazhe Xu, Trevor Darrell, Pieter Abbeel
<span title="2018-11-08">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We apply deep reinforcement learning techniques to training two out of six modules of a modular agent with self-play, achieving 94% or 87% win rates against the "Harder" (level 5) built-in Blizzard bot  ...  Modules in this framework can be optimized independently or jointly via human design, planning, or reinforcement learning.  ...  Self-Play We follow the self-play procedure suggested by Bansal et al. (2018) to save snapshots of the current agent into a training pool periodically (every 3 × 10 6 policy steps).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1811.03555v1">arXiv:1811.03555v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mzr7jha5pja4jmmlrybhyqtf6a">fatcat:mzr7jha5pja4jmmlrybhyqtf6a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200830075754/https://arxiv.org/pdf/1811.03555v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/98/7a/987ac9312951b4f1f7a17c687549eecc56adb3b9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1811.03555v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A Survey of Deep Reinforcement Learning in Video Games [article]

Kun Shao, Zhentao Tang, Yuanheng Zhu, Nannan Li, Dongbin Zhao
<span title="2019-12-26">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Besides, DRL plays an important role in game artificial intelligence (AI).  ...  This learning mechanism updates the policy to maximize the return with an end-to-end method.  ...  Asynchronous DRL is an efficient framework for DRL that uses asynchronous gradient descent to optimize the policy [33] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1912.10944v2">arXiv:1912.10944v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fsuzp2sjrfcgfkyclrsyzflax4">fatcat:fsuzp2sjrfcgfkyclrsyzflax4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321004953/https://arxiv.org/pdf/1912.10944v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1912.10944v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Analysis on the Roles of the Chinese Government in the Cultural Creative Industry Based on Public Expenditure Policies

Tian QIN, Xing KANG
<span title="2017-09-14">2017</span> <i title="DEStech Publications"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/lkpa7js6tvbo3ciwtdbpixgxjq" style="color: black;">DEStech Transactions on Economics Business and Management</a> </i> &nbsp;
The paper, mainly based the ten steps of public expenditure projects in the expenditure policy theory, analyzes the current roles of and influences from the Chinese Government on the cultural creative  ...  industry, explores the main functions and positioning of governments in the field, and then puts forward corresponding policy suggestions for helping local governments in China better plan and develop  ...  While participating in the development of the cultural creative industry, governments mainly play the functions of providing public cultural products, providing policy guidance, optimizing the environment  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.12783/dtem/icem2017/13106">doi:10.12783/dtem/icem2017/13106</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xj4lgfocurcz7jjsmgoitm45xa">fatcat:xj4lgfocurcz7jjsmgoitm45xa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180719101137/http://dpi-proceedings.com/index.php/dtem/article/download/13106/12634" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/6a/52/6a5204f5227ec1bb33cbd494b6ccd0a6c770babd.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.12783/dtem/icem2017/13106"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

The role of co-opetition in low carbon manufacturing

Zheng Luo, Xu Chen, Xiaojun Wang
<span title="">2016</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2fqqu5s6wbgk5gcucpt3wqm3gy" style="color: black;">European Journal of Operational Research</a> </i> &nbsp;
In addition, higher emission reduction efficiency leads to lower optimal unit carbon emissions and higher profit in both the pure competition and co-petition models.  ...  We investigate the pricing and emissions reduction policies for two rival manufacturers with different emission reduction efficiencies under the cap-and-trade policy.  ...  However, the co-opetition may also play an important role in achieving carbon efficient economy. This research seeks to address this gap.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.ejor.2016.02.030">doi:10.1016/j.ejor.2016.02.030</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bmhm2mk3xjd7lpw5rlamdcqsk4">fatcat:bmhm2mk3xjd7lpw5rlamdcqsk4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200322003033/https://research-information.bris.ac.uk/files/63693326/EJOR_coopetition_Low_carbon_manufacturing_accepted.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/f2/5c/f25ce8beee2d4f0de72c894fee3a361b768e34ce.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.ejor.2016.02.030"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

Research on the Strategies for Optimizing the Business Environment of Export-oriented Enterprises

Xingwu Yu, Weixing Wang, Ying Han
<span title="2010-01-18">2010</span> <i title="Canadian Center of Science and Education"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/doxdajfofzhxhnrpacrpjj3quu" style="color: black;">Asian Social Science</a> </i> &nbsp;
The governments and the industry or commercial associations at all levels should implement effective strategies to play their due role in optimizing the business environment of export-oriented enterprises  ...  Since China's accession to the WTO, export-oriented enterprises directly participate in international competition and face to increasingly environmental uncertainty and operational risk.  ...  " to bring the supportive and directive function of the policies into real play.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5539/ass.v6n2p108">doi:10.5539/ass.v6n2p108</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/43z33ikdo5dyjf5vqrgn24mdwy">fatcat:43z33ikdo5dyjf5vqrgn24mdwy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170922033347/http://www.ccsenet.org/journal/index.php/ass/article/download/5049/4197" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/f2/2d/f22d9cce7565f751c9e4f08205b75da063e06332.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5539/ass.v6n2p108"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

Dynamic Coevolution of Capital Allocation Efficiency of New Energy Vehicle Enterprises from Financing Niche Perspective

Qiong Wang, Cheng-xuan Geng, Hai-tao E
<span title="2019-05-02">2019</span> <i title="Hindawi Limited"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wpareqynwbgqdfodcyhh36aqaq" style="color: black;">Mathematical Problems in Engineering</a> </i> &nbsp;
With capital allocation efficiency as the core, adjusting the financing niche through financing market, industrial policy, enterprise development, and other factors will help to improve the coevolution  ...  Based on the dynamic characteristics of enterprises' competition and cooperation, this paper introduces the idea of ecology and synergy and constructs a dynamic coevolution model of financing allocation  ...  Secondly, the government should formulate effectively industrial policies, optimize the financing market and industrial financing niche, shore up weak spots of financing niche, give play to the decisive  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1155/2019/1412950">doi:10.1155/2019/1412950</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zbnewikitzbgvpsqpllrbkndba">fatcat:zbnewikitzbgvpsqpllrbkndba</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200212091840/http://downloads.hindawi.com/journals/mpe/2019/1412950.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/27/5f/275ff848e1d4c8cc298360c8c7978ff167963e07.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1155/2019/1412950"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> hindawi.com </button> </a>

Emergent Complexity via Multi-Agent Competition [article]

Trapit Bansal, Jakub Pachocki, Szymon Sidor, Ilya Sutskever, Igor Mordatch
<span title="2018-03-14">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we point out that a competitive multi-agent environment trained with self-play can produce behaviors that are far more complex than the environment itself.  ...  This work introduces several competitive multi-agent environments where agents compete in a 3D world with simulated physics.  ...  best self-play policy.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1710.03748v3">arXiv:1710.03748v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fy7zq4scajf7zh36gut2a7zwyy">fatcat:fy7zq4scajf7zh36gut2a7zwyy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200830154749/https://arxiv.org/pdf/1710.03748v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/a0/49/a049852827d0412aff150ac998656376b76b6e79.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1710.03748v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Improving Pension Management and Delivery: An (Im)Modest and Likely (Un)Popular Proposal

Ronald Geoffrey Bird, Jack Gray
<span title="">2009</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/tol7woxlqjeg5bmzadeg6qrg3e" style="color: black;">Social Science Research Network</a> </i> &nbsp;
The benefits of effective competition include innovation, lower costs, and greater efficiency.  ...  Two broad policy initiatives could achieve this three percent saving and move us closer to generating "optimal" 5 outcomes for members 6 : 1.  ...  Through its research funding and discussion forums, the Centre produces a steady stream of innovative insights into optimal pension system design and the effective management of pension delivery organizations  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2139/ssrn.1493342">doi:10.2139/ssrn.1493342</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ky73oqyp7bfmbfw4yvbfqytn4u">fatcat:ky73oqyp7bfmbfw4yvbfqytn4u</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170808165634/https://www.uts.edu.au/sites/default/files/DP1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/16/4d/164d840602602e3c52ea7dbda6f27f652d9ac2dd.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2139/ssrn.1493342"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ssrn.com </button> </a>

Page 98 of Journal of Science Education and Technology Vol. 8, Issue 2 [page]

<span title="">1999</span> <i title="Springer Science &amp; Business Media"> <a target="_blank" rel="noopener" href="https://archive.org/details/pub_journal-of-science-education-and-technology" style="color: black;">Journal of Science Education and Technology</a> </i> &nbsp;
School policy establishes the required courses and enforces student involvement in them.  ...  The “higher efficiency” river dumped the concentrated nutrients in the lake which biotically ‘“‘died’”’ from an overdose.  ... 
<span class="external-identifiers"> </span>
<a target="_blank" rel="noopener" href="https://archive.org/details/sim_journal-of-science-education-and-technology_1999-06_8_2/page/98" title="read fulltext microfilm" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Archive [Microfilm] <div class="menu fulltext-thumbnail"> <img src="https://archive.org/serve/sim_journal-of-science-education-and-technology_1999-06_8_2/__ia_thumb.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a>

Improved Robustness and Safety for Autonomous Vehicle Control with Adversarial Reinforcement Learning [article]

Xiaobai Ma, Katherine Driggs-Campbell, Mykel J. Kochenderfer
<span title="2019-03-08">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This paper examines two different algorithms to solve the game, Robust Adversarial Reinforcement Learning and Neural Fictitious Self Play, and compares performance on an autonomous driving scenario.  ...  The resulting robust policy exhibits improved driving efficiency while effectively reducing collision rates compared to baseline control policies produced by traditional reinforcement learning methods.  ...  However, with the addition of the cooperative reward and the averaging from fictitious self play, the protagonist and the adversary policies evolve more smoothly and converge more closely to the game's  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1903.03642v1">arXiv:1903.03642v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gotfm7u5dzh45onov6pdy4kjfe">fatcat:gotfm7u5dzh45onov6pdy4kjfe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200912043534/https://arxiv.org/pdf/1903.03642v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/fd/8b/fd8b3cac49da37d84ebd1d62c99311c7a086d7aa.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1903.03642v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 116,275 results