1138 search results - page 160 / 228 » Feature Markov Decision Processes |
157
Voted
ICML
2007
IEEE
16 years 4 months ago
2007
IEEE
We consider the problem of multi-task reinforcement learning, where the agent needs to solve a sequence of Markov Decision Processes (MDPs) chosen randomly from a fixed but unknow...
125
click to vote
ICML
2008
IEEE
16 years 4 months ago
2008
IEEE
We consider the task of reinforcement learning in an environment in which rare significant events occur independently of the actions selected by the controlling agent. If these ev...
125
click to vote
ICML
2006
IEEE
16 years 4 months ago
2006
IEEE
In the model-based policy search approach to reinforcement learning (RL), policies are found using a model (or "simulator") of the Markov decision process. However, for ...
141
click to vote
ICML
2006
IEEE
16 years 4 months ago
2006
IEEE
Reinforcement learning (RL) was originally proposed as a framework to allow agents to learn in an online fashion as they interact with their environment. Existing RL algorithms co...
124
click to vote
ICML
2003
IEEE
16 years 4 months ago
2003
IEEE
We investigate methods for planning in a Markov Decision Process where the cost function is chosen by an adversary after we fix our policy. As a running example, we consider a rob...