Planning with Macro-Actions in Decentralized POMDPs Christopher Amato, George D. Konidaris and Leslie P. Kaelbling MIT CSAIL Cambridge, MA 02139 {camato, gdk, lpk - Process agent - Document - PDFSEARCH.IO

First Page		Document Content
Date: 2014-02-13 11:20:11 Systems theory Mathematical optimization Markov processes Stochastic control Multi-agent systems Partially observable Markov decision process Automated planning and scheduling Markov decision process Action selection Statistics Dynamic programming Control theory		Planning with Macro-Actions in Decentralized POMDPs Christopher Amato, George D. Konidaris and Leslie P. Kaelbling MIT CSAIL Cambridge, MA 02139 {camato, gdk, lpk}@csail.mit.edu Add to Reading List Source URL: people.csail.mit.edu Download Document from Source Website File Size: 485,88 KB Share Document on Facebook

	Towards a high level programming paradigm to deploy e-science applications with dynamic workflows on large scale distributed systems Mohamed Ben Belgacem Nabil Abdennadher DocID: 1xTOs - View Document
	Minimax Differential Dynamic Programming: An Application to Robust Biped Walking Jun Morimoto Human Information Science Labs, Department 3, ATR International DocID: 1vqMk - View Document
	Empirical Dynamic Programming William B. Haskell ISE Department, National University of Singapore Rahul Jain* DocID: 1vouJ - View Document
	MarchRevised MayReport LIDS-P-3506 Stable Optimal Control and Semicontractive Dynamic Programming DocID: 1vhRF - View Document
	EE365: Deterministic Finite State Control Deterministic optimal control Shortest path problem Dynamic programming Examples DocID: 1vg0M - View Document