Markov decision process - PDFSEARCH.IO - Document Search Engine

Markov decision process
Results: 537

#	Item
91	Towards a Principled General Approach to Motion Planning under Uncertainty David Hsu National University of Singapore Add to Reading List Source URL: www.cse.unr.edu Language: English - Date: 2012-12-20 19:29:32 Control theory Robot Motion Mathematical sciences Motion planning Cybernetics Index of robotics articles Dynamic programming Partially observable Markov decision process Stochastic control
92	Learning Anticipation Policies for Robot Table Tennis Zhikun Wang1,2 , Christoph H. Lampert3 , Katharina Mülling1,2 , Bernhard Schölkopf1 , Jan Peters1,2 Abstract— Playing table tennis is a difficult task for robots, Add to Reading List Source URL: www.is.tuebingen.mpg.de Language: English - Date: 2011-10-10 12:02:25 Computing Software engineering Dynamic programming Reinforcement learning Table tennis Markov chain Robotics Robot Markov decision process Statistics Markov processes Markov models
93	Addressing the Policy-bias of Q-learning by Repeating Updates ∗ Sherief Abdallah Add to Reading List Source URL: michaelkaisers.com Language: English - Date: 2013-05-22 14:31:54 Q-learning Reinforcement learning Markov decision process Normal distribution Machine learning Statistics Markov models Markov processes
94	Stochastic and fluid index policies for resource allocation problems M. Larran˜aga1,2,5 , U. Ayesta2,3,4,5 , I.M. Verloop1,5 IRIT, 2 rue C. Carmichel, FToulouse, France. 2 CNRS, LAAS, 7 avenue du colonel Roche, F Add to Reading List Source URL: verloop.perso.enseeiht.fr Language: English - Date: 2015-04-01 14:42:52 Systems theory Dynamic programming Operations research Equations Optimal control Bellman equation Multi-armed bandit Markov decision process Relaxation Statistics Mathematical optimization Control theory
95	Reusable Sampling-Based Techniques for Manipulation via Pushing Christopher Vo Abstract—In this work, we consider the problem of manipulating a polygonal object through an obstacle-filled environment using only push in Add to Reading List Source URL: www.cse.unr.edu Language: English - Date: 2012-12-20 19:29:59 Theoretical computer science Kinodynamic planning International Conference On Intelligent Robots and Systems Partially observable Markov decision process Robot ROS Cognitive robotics Robotics Robot kinematics Motion planning
96	Using Iterated Reasoning to Predict Opponent Strategies Michael Wunder Michael Kaisers Rutgers University Add to Reading List Source URL: michaelkaisers.com Language: English - Date: 2012-04-29 08:04:26 Science Dynamic programming Markov processes Stochastic control Control theory Partially observable Markov decision process Automated planning and scheduling Multi-agent system Markov decision process Game theory Statistics Artificial intelligence
97	Shared Autonomy via Hindsight Optimization Shervin Javdani, Siddhartha S. Srinivasa, J. Andrew Bagnell The Robotics Institute, Carnegie Mellon University {sjavdani, siddh, dbagnell}@cs.cmu.edu Abstract—In shared autono Add to Reading List Source URL: www.ri.cmu.edu Language: English - Date: 2015-05-06 09:31:40 Stochastic control Virtual reality Control theory Mathematics Partially observable Markov decision process User interface Markov decision process Virtual fixture Lyapunov stability Statistics Dynamic programming Markov processes
98	Reusable Sampling-Based Techniques for Manipulation via Pushing Christopher Vo Abstract—In this work, we consider the problem of manipulating a polygonal object through an obstacle-filled environment using only push in Add to Reading List Source URL: iros2011.org Language: English - Date: 2011-09-21 07:00:45 Theoretical computer science Kinodynamic planning International Conference On Intelligent Robots and Systems Partially observable Markov decision process Robot ROS Cognitive robotics Robotics Robot kinematics Motion planning
99	Stochastic and fluid index policies for resource allocation problems M. Larran˜aga1,2,5 , U. Ayesta2,3,4,5 , I.M. Verloop1,5 IRIT, 2 rue C. Carmichel, FToulouse, France. 2 CNRS, LAAS, 7 avenue du colonel Roche, F Add to Reading List Source URL: homepages.laas.fr Language: English - Date: 2015-02-17 15:01:29 Systems theory Dynamic programming Operations research Equations Optimal control Bellman equation Multi-armed bandit Markov decision process Relaxation Statistics Mathematical optimization Control theory
100	Asymptotically optimal index policies for an abandonment queue with convex holding cost∗ M. Larra˜ naga1,2,5 , U. Ayesta2,3,4,5 , I.M. Verloop1,5 1 CNRS, IRIT, 2 rue C. Carmichel, FToulouse, France. Add to Reading List Source URL: homepages.laas.fr Language: English - Date: 2015-04-15 10:57:22 Dynamic programming Optimal control Mathematical sciences Markov decision process Relaxation Mathematical optimization Statistics Operations research