Deep Learning for Reward Design to Improve Monte Carlo Tree Search in ATARI Games Xiaoxiao Guo, Satinder Singh, Richard Lewis, Honglak Lee University of Michigan, Ann Arbor {guoxiao,baveja,rickl,honglak - Elland Lower Edge - Document - PDFSEARCH.IO

First Page		Document Content
Date: 2016-04-22 16:33:09 Neuroscience Artificial intelligence Machine learning Machine learning algorithms Computational neuroscience Artificial neural networks Q-learning Reinforcement learning University of Cape Town Monte Carlo tree search Sepp Hochreiter Convolutional neural network		Deep Learning for Reward Design to Improve Monte Carlo Tree Search in ATARI Games Xiaoxiao Guo, Satinder Singh, Richard Lewis, Honglak Lee University of Michigan, Ann Arbor {guoxiao,baveja,rickl,honglak}@umich.edu Add to Reading List Source URL: web.eecs.umich.edu Download Document from Source Website File Size: 1,19 MB Share Document on Facebook

	Machine Learning for Q&A sites: state of the art and research directions Xavier Amatriain Quora Inc. 650 Castro St #450 Mountain View, CA, US DocID: 1xVAM - View Document
	MITSUBISHI ELECTRIC RESEARCH LABORATORIES http://www.merl.com Learning to Control Partial Differential Equations: Regularized Fitted Q-Iteration Approach Farahmand, A.-M.; Nabi, S.; Grover, P.; Nikovski, D.N. DocID: 1vimT - View Document
	Deep Q-learning from Demonstrations Matej Vecerik Todd Hester Olivier Pietquin DocID: 1vgGk - View Document
	Session 5 Relaxed dynamic programming and Q-learning Reading assignment Check the main results and examples of these papers. • Lincoln/Rantzer, TAC 51:) DocID: 1uUGg - View Document
	L5: Relaxed dynamic programming and Q-learning • Relaxed Dynamic Programming DocID: 1uO6O - View Document