Filters








1,277 Hits in 5.9 sec

Action-Conditional Video Prediction using Deep Networks in Atari Games [article]

Junhyuk Oh, Xiaoxiao Guo, Honglak Lee, Richard Lewis, Satinder Singh
<span title="2015-12-22">2015</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We propose and evaluate two deep neural network architectures that consist of encoding, action-conditional transformation, and decoding layers based on convolutional neural networks and recurrent neural  ...  Motivated by vision-based reinforcement learning (RL) problems, in particular Atari games from the recent benchmark Aracade Learning Environment (ALE), we consider spatio-temporal prediction problems where  ...  Related Work Video Prediction using Deep Networks. The problem of video prediction has led to a variety of architectures in deep learning.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1507.08750v2">arXiv:1507.08750v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4kkpao5tzbfghk5lkzsegrdpxq">fatcat:4kkpao5tzbfghk5lkzsegrdpxq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200829001142/https://arxiv.org/pdf/1507.08750v2.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/80/b9/80b9c126a3809b4c8306cb339db542bc456d548f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1507.08750v2" 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>

Model-Based Regularization for Deep Reinforcement Learning with Transcoder Networks [article]

Felix Leibfried, Peter Vrancx
<span title="2018-11-20">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The prediction errors for the model are included in the basic DQN loss as additional regularizers.  ...  We extend conventional Deep Q-Networks (DQNs) by adding a model-learning component yielding a transcoder network.  ...  acting and prediction; • demonstrate accurate future video frame and reward prediction in ALE; • and outperform deep RL without model-based regularization on several Atari games.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1809.01906v2">arXiv:1809.01906v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2n7mubkcdfcyrebnku5nbsh2h4">fatcat:2n7mubkcdfcyrebnku5nbsh2h4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200927172515/https://arxiv.org/pdf/1809.01906v2.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/0e/aa/0eaa2616bf65233eb3a5ea63262913015914dce7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1809.01906v2" 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>

Benchmarking End-to-End Behavioural Cloning on Video Games [article]

Anssi Kanervisto, Joonas Pussinen, Ville Hautamäki
<span title="2020-05-18">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We take a step towards a general approach and study the general applicability of behavioural cloning on twelve video games, including six modern video games (published after 2010), by using human demonstrations  ...  As a general approach to playing video games, this has many inviting properties: no need for specialized modifications to the game, no lengthy training sessions and the ability to re-use the same tools  ...  To model the conditional distribution p(a|s), we use deep neural networks. They support the different actions we could have and are known to excel in image classification tasks [24] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2004.00981v2">arXiv:2004.00981v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vuucimtf3jhnflk7jxkf3cld5m">fatcat:vuucimtf3jhnflk7jxkf3cld5m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200520002521/https://arxiv.org/pdf/2004.00981v2.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/2004.00981v2" 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 Deep Learning Approach for Joint Video Frame and Reward Prediction in Atari Games [article]

Felix Leibfried, Nate Kushman, Katja Hofmann
<span title="2017-08-17">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Our contribution is to extend a recently developed deep neural network for video frame prediction in Atari games to enable reward prediction as well.  ...  State-of-the-art reinforcement learning approaches, such as deep Q-networks, are model-free and learn to act effectively across a wide range of environments such as Atari games, but require huge amounts  ...  in a given state, using deep neural networks.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1611.07078v2">arXiv:1611.07078v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/brs5gs7r4raslcqibwmillfwri">fatcat:brs5gs7r4raslcqibwmillfwri</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191024090948/https://arxiv.org/pdf/1611.07078v2.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/55/1d/551db45d4157f012040bd157789541389eb33ac1.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1611.07078v2" 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>

Disentangling Controllable Object through Video Prediction Improves Visual Reinforcement Learning [article]

Yuanyi Zhong, Alexander Schwing, Jian Peng
<span title="2020-02-21">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Leveraging action-conditioned video prediction, we propose an end-to-end learning framework to disentangle the controllable object from the observation signal.  ...  Experiments on a set of Atari games with the popular Double DQN algorithm demonstrate improved sample efficiency and game performance (from 222.8% to 261.4% measured in normalized game scores, with prediction  ...  [1, 2] , and video game playing in Atari games [3] , StarCraft II [4] and Dota 2 [5] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.09136v1">arXiv:2002.09136v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bw3iyw3gnfhtlldylcxxdwcb7e">fatcat:bw3iyw3gnfhtlldylcxxdwcb7e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200322022526/https://arxiv.org/pdf/2002.09136v1.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/2002.09136v1" 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>

Deep Learning for Video Game Playing [article]

Niels Justesen, Philip Bontrager, Julian Togelius, Sebastian Risi
<span title="2019-02-18">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this article, we review recent Deep Learning advances in the context of how they have been applied to play different types of video games such as first-person shooters, arcade games, and real-time strategy  ...  We analyze the unique requirements that different game genres pose to a deep learning system and highlight important open challenges in the context of applying these machine learning methods to video games  ...  This predictive model could then be used for planning actions in the game.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1708.07902v3">arXiv:1708.07902v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/f3bp2y3khbhqhm5cm3hfqwdtna">fatcat:f3bp2y3khbhqhm5cm3hfqwdtna</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200827152721/https://arxiv.org/pdf/1708.07902v3.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/c3/b0/c3b0aeb9fcf17b27e1d96cae1494cf815492c1ed.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1708.07902v3" 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>

PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learning [article]

Tao Yu, Cuiling Lan, Wenjun Zeng, Mingxiao Feng, Zhizheng Zhang, Zhibo Chen
<span title="2021-10-27">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Specifically, PlayVirtual predicts future states in the latent space based on the current state and action by a dynamics model and then predicts the previous states by a backward dynamics model, which  ...  ., state-action sequences), the lack of data limits the use of them for better feature learning.  ...  This holds in most games such as chess or Atari.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.04152v2">arXiv:2106.04152v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xqenwwweifbe3egxhaq3ow7fzi">fatcat:xqenwwweifbe3egxhaq3ow7fzi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210614110629/https://arxiv.org/pdf/2106.04152v1.pdf" title="fulltext PDF download [not primary version]" 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] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/a0/b2/a0b240e5fea6c56ef9da60367902b507118eafb9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.04152v2" 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>

Noisy Agents: Self-supervised Exploration by Predicting Auditory Events [article]

Chuang Gan, Xiaoyu Chen, Phillip Isola, Antonio Torralba, Joshua B. Tenenbaum
<span title="2020-07-27">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We then train a neural network to predict the auditory events and use the prediction errors as intrinsic rewards to guide RL exploration.  ...  In this work, we propose a novel type of intrinsic motivation for Reinforcement Learning (RL) that encourages the agent to understand the causal effect of its actions through auditory event prediction.  ...  In the second phase, we train a neural network to predict the auditory events conditioned on the embedding of visual observations and actions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.13729v1">arXiv:2007.13729v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yvlz2stdxnckbnacgyc7rjmrui">fatcat:yvlz2stdxnckbnacgyc7rjmrui</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200829012621/https://arxiv.org/pdf/2007.13729v1.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/5f/97/5f978b3829acad6ac8b3372d2fa8d38a45b96d3d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.13729v1" 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>

Transparency and Explanation in Deep Reinforcement Learning Neural Networks [article]

Rahul Iyer, Yuezhang Li, Huao Li, Michael Lewis, Ramitha Sundar, Katia Sycara
<span title="2018-09-17">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Such networks have been extremely successful in accurately learning action control in image input domains, such as Atari games.  ...  In recent years, Deep Neural Networks have made great advances in multiple application areas. However, deep neural networks are opaque.  ...  After the action, the agent observes a scalar reward r t and receives the next state s t+1 . In the Atari games, the input current state is an image.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1809.06061v1">arXiv:1809.06061v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/o4qe4ykrl5emba53sxchvmen5q">fatcat:o4qe4ykrl5emba53sxchvmen5q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191022062226/https://arxiv.org/pdf/1809.06061v1.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/97/fa/97faf17bcee8efa41686ab4383efaba6026de29b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1809.06061v1" 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>

At Human Speed: Deep Reinforcement Learning with Action Delay [article]

Vlad Firoiu, Tina Ju, Josh Tenenbaum
<span title="2018-10-16">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Many classes of tasks, from video games to motor control to board games, are now solvable by fairly generic algorithms, based on deep learning and reinforcement learning, that learn to play from experience  ...  We propose a solution to the action delay problem inspired by human perception -- to endow agents with a neural predictive model of the environment which "undoes" the delay inherent in their environment  ...  Video games, starting with classic Atari console titles, were among the first to be tackled by deep RL (cite DQN), and are still widely used as benchmarks for state-of-the-art RL algorithms today.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1810.07286v1">arXiv:1810.07286v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cujdicoa5vhl7hfen363v7z6ua">fatcat:cujdicoa5vhl7hfen363v7z6ua</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200912125208/https://arxiv.org/pdf/1810.07286v1.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/0d/28/0d285173234fbc290b9d8b5a6ddf5db4cc1eae7c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1810.07286v1" 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>

Task-Agnostic Dynamics Priors for Deep Reinforcement Learning [article]

Yilun Du, Karthik Narasimhan
<span title="2019-07-11">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In fact, humans continuously acquire and use such dynamics priors to easily adapt to operating in new environments.  ...  In this work, we propose an approach to learn task-agnostic dynamics priors from videos and incorporate them into an RL agent.  ...  In contrast, we learn physics priors in the form of the parameters of a predictive neural network, only using raw videos. Decoupling dynamics from policy.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1905.04819v4">arXiv:1905.04819v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rupfjffiozg67ijipshvv5abr4">fatcat:rupfjffiozg67ijipshvv5abr4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200915093726/https://arxiv.org/pdf/1905.04819v2.pdf" title="fulltext PDF download [not primary version]" 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] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e6/5f/e65f025faf8cf173640b216a0464a0ba0dec2c5d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1905.04819v4" 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>
Generally, DRL agents receive high-dimensional inputs at each step, and make actions according to deep-neural-network-based policies.  ...  We also take a review of the achievements of DRL in various video games, including classical Arcade games, first-person perspective games and multi-agent real-time strategy games, from 2D to 3D, and from  ...  The framework diagram of typical DRL for video games is depicted in Fig. 1 . A. Deep learning Deep learning comes from artificial neural networks, and is used to learn data representation.  ... 
<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>

Model-Based Reinforcement Learning for Atari [article]

Lukasz Kaiser, Mohammad Babaeizadeh, Piotr Milos, Blazej Osinski, Roy H Campbell, Konrad Czechowski, Dumitru Erhan, Chelsea Finn, Piotr Kozakowski, Sergey Levine, Afroz Mohiuddin, Ryan Sepassi, George Tucker (+1 others)
<span title="2020-02-19">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we explore how video prediction models can similarly enable agents to solve Atari games with fewer interactions than model-free methods.  ...  Part of the answer may be that people can learn how the game works and predict which actions will lead to desirable outcomes.  ...  In particular, Konrad Czechowski, Piotr Kozakowski, Henryk Michalewski, Piotr Miłoś and Błażej Osiński extensively used the Prometheus supercomputer, located in the Academic Computer Center Cyfronet in  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1903.00374v4">arXiv:1903.00374v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/y6o3luqnxbhvfdc4l7yiabufni">fatcat:y6o3luqnxbhvfdc4l7yiabufni</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321064847/https://arxiv.org/pdf/1903.00374v4.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/1903.00374v4" 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>

Playable Video Generation

Willi Menapace, Stephane Lathuiliere, Sergey Tulyakov, Aliaksandr Siarohin, Elisa Ricci
<span title="2021-06-22">2021</span> <i title="Zenodo"> Zenodo </i> &nbsp;
The network is constrained to learn a rich action space using, as main driving loss, a reconstruction loss on the generated video.  ...  The difficulty of the task lies both in learning semantically consistent actions and in generating realistic videos conditioned on the user input.  ...  We collect a dataset using a Rainbow DQN agent [15] trained on the Atari Breakout video game environment.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5281/zenodo.5014666">doi:10.5281/zenodo.5014666</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/csx2d5le7jfzrkxpqnflemuinm">fatcat:csx2d5le7jfzrkxpqnflemuinm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210623021015/https://zenodo.org/record/5014666/files/Menapace_Playable_Video_Generation_CVPR_2021_paper.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/dd/d4/ddd4094a9cb139d820bdf0e0d3fd0e1853a13692.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5281/zenodo.5014666"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> zenodo.org </button> </a>

Playable Video Generation [article]

Willi Menapace, Stéphane Lathuilière, Sergey Tulyakov, Aliaksandr Siarohin, Elisa Ricci
<span title="2021-01-28">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The network is constrained to learn a rich action space using, as main driving loss, a reconstruction loss on the generated video.  ...  The difficulty of the task lies both in learning semantically consistent actions and in generating realistic videos conditioned on the user input.  ...  We collect a dataset using a Rainbow DQN agent [15] trained on the Atari Breakout video game environment.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2101.12195v1">arXiv:2101.12195v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rl2xllly2zb4ddhrbumt5elgrm">fatcat:rl2xllly2zb4ddhrbumt5elgrm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210131040950/https://arxiv.org/pdf/2101.12195v1.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/fa/90/fa904504a5ab2a2fa6f59638e6dec37714d729bb.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2101.12195v1" 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 1,277 results