Sample-efficient iterative lower bound optimization of deep reactive policies for planning in continuous MDPs

Sample-efficient iterative lower bound optimization of deep reactive policies for planning in continuous MDPs

Recent advances in deep learning have enabled optimization of deep reactive policies (DRPs) for continuous MDP planning by encoding a parametric policy as a deep neural network and exploiting automatic differentiation in an end-toend model-based gradient descent framework. This approach has proven e...

Saved in:

書目詳細資料
Main Authors:	LOW, Siow Meng, KUMAR, Akshat, SANNER, Scott
格式:	text
語言:	English
出版:	Institutional Knowledge at Singapore Management University 2022
主題:	Artificial Intelligence and Robotics
在線閱讀:	https://ink.library.smu.edu.sg/sis_research/7724 https://ink.library.smu.edu.sg/context/sis_research/article/8727/viewcontent/21220_Article_Text_25233_1_2_20220628.pdf
標簽:	添加標簽沒有標簽, 成為第一個標記此記錄!
機構:	Singapore Management University
語言:	English

相似書籍

Sampling based approaches for minimizing regret in uncertain Markov Decision Problems (MDPs)
由: AHMED, Asrar, et al.
出版: (2017)

Event-Detecting Multi-Agent MDPs: Complexity and Constant-Factor Approximation
由: KUMAR, Akshat, et al.
出版: (2009)

Solving long-run average reward robust MDPs via stochastic games
由: CHATTERJEE, Krishnendu, et al.
出版: (2024)

History-Based Controller Design and Optimization for Partially Observable MDPs
由: KUMAR, Akshat, et al.
出版: (2015)

Unleashing Dec-MDPs in Security Games: Enabling Effective Defender Teamwork
由: Shieh, Eric, et al.
出版: (2014)

Safe MDP planning by learning temporal patterns of undesirable trajectories and averting negative side effects
由: LOW, Siow Meng, et al.
出版: (2023)

PLANNING UNDER UNCERTAINTY: FROM INFORMATIVE PATH PLANNING TO PARTIALLY OBSERVABLE SEMI-MDPS
由: LIM ZHAN WEI
出版: (2015)

Revisiting Risk-Sensitive MDPs: New Algorithms and Results
由: HOU, Ping, et al.
出版: (2014)

An extended study on addressing defender teamwork while accounting for uncertainty in attacker defender games using iterative Dec-MDPs
由: SHIEH, Eric, et al.
出版: (2016)

A mixed-integer linear programming reduction of disjoint bilinear programs via symbolic variable elimination
由: JEONG, Jihwan, et al.
出版: (2023)

Parameter Learning for Latent Network Diffusion
由: WU, Xiaojian, et al.
出版: (2013)

Certified policy verification and synthesis for MDPs under distributional reach-avoidance properties
由: AKSHAY, S., et al.
出版: (2024)

Deep one-class classification via interpolated Gaussian descriptor
由: CHEN, Yuanhong, et al.
出版: (2022)

Learning expensive coordination: An event-based deep RL approach
由: YU, Runsheng, et al.
出版: (2020)

Collective Diffusion Over Networks: Models and Inference
由: KUMAR, Akshat, et al.
出版: (2013)

Automated Generation of Interaction Graphs for Value-Factored Decentralized POMDPs
由: YEOH, William, et al.
出版: (2013)

Lagrangian Relaxation Techniques for Scalable Spatial Conservation Planning
由: KUMAR, Akshat, et al.
出版: (2012)

H-DPOP: Using Hard Constraints for Search Space Pruning in DCOP
由: KUMAR, Akshat, et al.
出版: (2008)

Probabilistic Inference Techniques for Scalable Multiagent Decision Making
由: Akshat KUMAR,, et al.
出版: (2015)

Learning and Controlling Network Diffusion in Dependent Cascade Models
由: DU, Jiali, et al.
出版: (2015)

Robust decision making for stochastic network design
由: Akshat KUMAR,, et al.
出版: (2016)

Distributed Gibbs: A memory-bounded sampling-based DCOP algorithm
由: NGUYEN, Duc Thien, et al.
出版: (2013)

Using constraint programming and graph representation learning for generating interpretable cloud security policies
由: KAZDAGLI, Mikhail, et al.
出版: (2022)

Solving Uncertain MDPs with Objectives that are Separable over Instantiations of Model Uncertainty
由: ADULYASAK, Yossiri, et al.
出版: (2015)

Building action sets in a deep reinforcement learner
由: WANG, Yongzhao, et al.
出版: (2021)

Explainable deep few-shot anomaly detection with deviation networks
由: PANG, Guansong, et al.
出版: (2021)

FlowPG: Action-constrained policy gradient with normalizing flows
由: BRAHMANAGE JANAKA CHATHURANGA THILAKARATHNA,, et al.
出版: (2023)

Learning transferable deep convolutional neural networks for the classification of bacterial virulence factors
由: ZHENG, Dandan, et al.
出版: (2020)

Norm-based generalisation bounds for deep multi-class convolutional neural networks
由: LEDENT, Antoine, et al.
出版: (2021)

A balanced view of artificial intelligence
由: Ngo, Courtney Anne M.
出版: (2018)

Can we regulate artificial intelligence?
由: Javier, Cholo E.
出版: (2024)

How to think like an AI
由: Lugtu, Reynaldo C., Jr.
出版: (2024)

Is AI making us smarter or dumber?
由: Lugtu, Reynaldo C.
出版: (2024)

The rise of generation AI
由: Lugtu, Reynaldo C., Jr.
出版: (2025)

Teaching use of AI with meta-reflections
由: Aure, Patrick Adriel H.
出版: (2023)

Iterated Weaker-than-Weak Dominance
由: CHENG, Shih-Fen, et al.
出版: (2007)

Influence Diagrams With Memory States: Representation and Algorithms
由: WU, Xiaojian, et al.
出版: (2011)

An approach for self-training audio event detectors using web data
由: ELIZALDE, Benjamin, et al.
出版: (2017)

Spectral tensor train parameterization of deep learning layers
由: OBUKHOV, A., et al.
出版: (2021)

Scalable and globally optimal generalized L1 K-center clustering via constraint generation in mixed integer linear programming
由: CHEMBU, Aravinth, et al.
出版: (2023)