67,454 Hits in 3.6 sec

Deep Sets for Generalization in RL [article]

Tristan Karch, Cédric Colas, Laetitia Teodorescu, Clément Moulin-Frier, Pierre-Yves Oudeyer
2020 arXiv   pre-print
This is done using a combination of object-wise permutation invariant networks inspired from Deep Sets and gated-attention mechanisms.  ...  In a 2D procedurally-generated world where agents targeting goals in natural language navigate and interact with objects, we show that these architectures demonstrate strong generalization capacities to  ...  DEEP SETS FOR RL The agent learns in parallel a language model, an internal goal-conditioned reward function and a multi-goal policy.  ... 
arXiv:2003.09443v1 fatcat:ybbvjsajxzeulkfpdquko3pk4a

Generalization of Reinforcement Learning with Policy-Aware Adversarial Data Augmentation [article]

Hanping Zhang, Yuhong Guo
2021 arXiv   pre-print
The generalization gap in reinforcement learning (RL) has been a significant obstacle that prevents the RL agent from learning general skills and adapting to varying environments.  ...  more effectively increase the RL agent's generalization ability with the policy-aware data augmentation.  ...  Method This study focuses on increasing the generalization ability of a deep RL agent. Following the previous generalization study in RL [18] , we consider the following RL setting.  ... 
arXiv:2106.15587v2 fatcat:5emc4oswtzf27e3yjn6l5hj6nq

Hyperparameter Tuning for Deep Reinforcement Learning Applications [article]

Mariam Kiran, Melis Ozyildirim
2022 arXiv   pre-print
However, setting the right hyperparameters can have a huge impact on the deployed solution performance and reliability in the inference models, produced via RL, used for decision-making.  ...  In comparison to other neural network architectures, deep RL has not witnessed much hyperparameter tuning, due to its algorithm complexity and simulation platforms needed.  ...  HPS-RL Deep RL algorithms HPS-RL packages its deep RL algorithms for researchers to explore. HPS-RL provides more deep RL algorithms listed in Table 1 .  ... 
arXiv:2201.11182v1 fatcat:ilhx5djtlzbcdcohcax6mj5dda

Assessing Generalization in Deep Reinforcement Learning [article]

Charles Packer, Katelyn Gao, Jernej Kos, Philipp Krähenbühl, Vladlen Koltun, Dawn Song
2019 arXiv   pre-print
As a result, deep RL algorithms that promote generalization are receiving increasing attention. However, works in this area use a wide variety of tasks and experimental setups for evaluation.  ...  Our framework contains a diverse set of environments, our methodology covers both in-distribution and out-of-distribution generalization, and our evaluation includes deep RL algorithms that specifically  ...  Acknowledgments This material is in part based upon work supported by the National Science Foundation under Grant No. TWC-1409915, DARPA under FA8750-17-2-0091, and Berkeley Deep Drive.  ... 
arXiv:1810.12282v2 fatcat:riywyt5j3fgnve473bg27kxjri

Where Did You Learn That From? Surprising Effectiveness of Membership Inference Attacks Against Temporally Correlated Data in Deep Reinforcement Learning [article]

Maziar Gomrokchi, Susan Amin, Hossein Aboutalebi, Alexander Wong, Doina Precup
2021 arXiv   pre-print
In particular, there have been no concrete adversarial attack strategies in literature tailored for studying the vulnerability of deep reinforcement learning algorithms to membership inference attacks.  ...  To address this gap, we propose an adversarial attack framework tailored for testing the vulnerability of deep reinforcement learning algorithms to membership inference attacks.  ...  ACKNOWLEDGEMENTS The authors would like to thank Hamidreza Ghafghazi for his valuable contribution to the design and development of the preliminary version of the codebase.  ... 
arXiv:2109.03975v2 fatcat:aktgp5aefzcj5hs7acymclg23m

Zero-shot Deep Reinforcement Learning Driving Policy Transfer for Autonomous Vehicles based on Robust Control [article]

Zhuo Xu, Chen Tang, Masayoshi Tomizuka
2018 arXiv   pre-print
Although deep reinforcement learning (deep RL) methods have lots of strengths that are favorable if applied to autonomous driving, real deep RL applications in autonomous driving have been slowed down  ...  in autonomous driving.  ...  In this framework, the deep RL policy is applied to an imaginary setting in the source domain to generate a reference trajectory for the target vehicle.  ... 
arXiv:1812.03216v1 fatcat:vfrcbl3wrzcjrkdok4qzbrqkta

Integrating Deep Reinforcement Learning Networks with Health System Simulations [article]

Michael Allen, Thomas Monks
2020 arXiv   pre-print
and motivation: Combining Deep Reinforcement Learning (Deep RL) and Health Systems Simulations has significant potential, for both research into improving Deep RL performance and safety, and in operational  ...  Aim: Provide a framework for integrating Deep RL Networks with Health System Simulations, and to ensure this framework is compatible with Deep RL agents that have been developed and tested using OpenAI  ...  Generic simulation methods The simulation is set up with three methods that interface the Deep RL agent and the simulation: • reset: resets the sim to a starting state and returns the first set of state  ... 
arXiv:2008.07434v1 fatcat:6xtq2ms7frcdrgnndjtr2l5fmq

An Introduction to Deep Reinforcement Learning

Vincent François-Lavet, Peter Henderson, Riashat Islam, Marc G. Bellemare, Joelle Pineau
2018 Foundations and Trends® in Machine Learning  
Particular focus is on the aspects related to generalization and how deep RL can be used for practical applications. We assume the reader is familiar with basic machine learning concepts.  ...  Thus, deep RL opens up many new applications in domains such as healthcare, robotics, smart grids, finance, and many more.  ...  We provide descriptions of how deep RL can be used in these settings. In Chapter 11, we present broader perspectives on deep RL.  ... 
doi:10.1561/2200000071 fatcat:gh3odyludnc43oeiqrgrtaer3u

Experienced Deep Reinforcement Learning with Generative Adversarial Networks (GANs) for Model-Free Ultra Reliable Low Latency Communication [article]

Ali Taleb Zadeh Kasgari, Walid Saad, Mohammad Mozaffari, H. Vincent Poor
2020 arXiv   pre-print
In particular, in order to enable the deep-RL framework to account for extreme network conditions and operate in highly reliable systems, a new approach based on generative adversarial networks (GANs)  ...  In this paper, a novel experienced deep reinforcement learning (deep-RL) framework is proposed to provide model-free resource allocation for ultra reliable low latency communication (URLLC).  ...  This large set of actions makes the problem unsuitable for deep-RL frameworks [30] .  ... 
arXiv:1911.03264v2 fatcat:cqr6p3aionfflc4a7py44t3icu

Deriving AC OPF Solutions via Proximal Policy Optimization for Secure and Economic Grid Operation [article]

Yuhao Zhou, Bei Zhang, Chunlei Xu, Tu Lan, Ruisheng Diao, Di Shi, Zhiwei Wang, Wei-Jen Lee
2020 arXiv   pre-print
Optimal power flow (OPF) is a very fundamental but vital optimization problem in the power system, which aims at solving a specific objective function (ex.: generator costs) while maintaining the system  ...  in the stable and safe operations.  ...  Generic Grid Environment used for Deep RL In this paper, the environment is developed by mimicking the OpenAI Gym environments, which are the benchmark systems used for deep RL studies.  ... 
arXiv:2003.12584v2 fatcat:c2zdfpgvffchpiml3fkfsnbhka

Mitigating Multi-Stage Cascading Failure by Reinforcement Learning [article]

Yongli Zhu, Chengxi Liu
2019 arXiv   pre-print
Experiments on the IEEE 118-bus system by both shallow and deep neural networks demonstrate promising results in terms of reduced system collapse rates.  ...  The problem is then tackled by the RL based on DC-OPF (Optimal Power Flow). Designs of the key elements of the RL framework (rewards, states, etc.) are also discussed in detail.  ...  G, D, L are respectively the generator set, load set and branch set; F=[Fl] (l∈L) represents the branch flow; pi (i∈G) is the generation dispatch for the i-th generator; pj (j∈D) is the load dispatch for  ... 
arXiv:1908.06599v1 fatcat:qliut6hv7bbzxhyxc36wnxyzsa

Reinforcement Learning, Fast and Slow

Mathew Botvinick, Sam Ritter, Jane X. Wang, Zeb Kurth-Nelson, Charles Blundell, Demis Hassabis
2019 Trends in Cognitive Sciences  
Deep reinforcement learning (RL) methods have driven impressive advances in artificial intelligence in recent years, exceeding human performance in domains ranging from Atari to Go to no-limit poker.  ...  Although these techniques were developed in an AI context, we propose that they may have rich implications for psychology and neuroscience.  ...  Sources of Slowness in Deep RL A key starting point for considering techniques for fast RL is to examine why initial methods for deep RL were in fact so slow.  ... 
doi:10.1016/j.tics.2019.02.006 pmid:31003893 fatcat:si5w44z7ybc6ln6linnd2j6cfi

Diversity-Promoting Deep Reinforcement Learning for Interactive Recommendation [article]

Yong Liu, Yinan Zhang, Qiong Wu, Chunyan Miao, Lizhen Cui, Binqiang Zhao, Yin Zhao, Lu Guan
2019 arXiv   pre-print
In this paper, we propose a novel recommendation model, named Diversity-promoting Deep Reinforcement Learning (D^2RL), which encourages the diversity of recommendation results in interaction recommendations  ...  More specifically, we adopt a Determinantal Point Process (DPP) model to generate diverse, while relevant item recommendations.  ...  Deep Reinforcement Learning Framework In the interactive recommendation setting of D 2 RL, the recommender system (i.e., agent) interacts with users (i.e., environment) by sequentially recommending a set  ... 
arXiv:1903.07826v1 fatcat:s5nlfafmvjhmlct5gar2qkcrc4

Interactive Narrative Personalization with Deep Reinforcement Learning

Pengcheng Wang, Jonathan Rowe, Wookhee Min, Bradford Mott, James Lester
2017 Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence  
In this paper we present a deep RL-based interactive narrative generation framework that leverages synthetic data produced by a bipartite simulated player model.  ...  Results suggest that the deep RL-based narrative generation framework yields effective personalized interactive narratives.  ...  In this work, we adapt this simulated user approach by inducing a bipartite player simulation model for generating synthetic training episodes for deep RL-based interactive narrative personalization.  ... 
doi:10.24963/ijcai.2017/538 dblp:conf/ijcai/WangRMML17 fatcat:3kcbhqznxvhu7obxb4r5qvkg7e

Deep Reinforcement Learning and its Neuroscientific Implications [article]

Matthew Botvinick, Jane X. Wang, Will Dabney, Kevin J. Miller, Zeb Kurth-Nelson
2020 arXiv   pre-print
Deep RL offers a comprehensive framework for studying the interplay among learning, representation and decision-making, offering to the brain sciences a new set of research tools and a wide range of novel  ...  In the present review, we provide a high-level introduction to deep RL, discuss some of its initial applications to neuroscience, and survey its wider implications for research on brain and behavior, concluding  ...  for generating them.  ... 
arXiv:2007.03750v1 fatcat:nl6ggmxli5fjlnub6y2w6nnvpe
« Previous Showing results 1 — 15 out of 67,454 results