1138 search results - page 128 / 228 » Feature Markov Decision Processes |
122
click to vote
IJCAI
2007
15 years 2 months ago
2007
Inverse Reinforcement Learning (IRL) is the problem of learning the reward function underlying a Markov Decision Process given the dynamics of the system and the behaviour of an e...
100
click to vote
IJCAI
2007
15 years 2 months ago
2007
A long-lived agent continually faces new tasks in its environment. Such an agent may be able to use knowledge learned in solving earlier tasks to produce candidate policies for it...
105
click to vote
UAI
2008
15 years 2 months ago
2008
Approximate linear programming (ALP) is an efficient approach to solving large factored Markov decision processes (MDPs). The main idea of the method is to approximate the optimal...
121
click to vote
AAAI
2004
15 years 2 months ago
2004
We develop an exact dynamic programming algorithm for partially observable stochastic games (POSGs). The algorithm is a synthesis of dynamic programming for partially observable M...
AAAI
2006
15 years 2 months ago
2006
Markov decision processes (MDPs) with discrete and continuous state and action components can be solved efficiently by hybrid approximate linear programming (HALP). The main idea ...