2005 search results - page 195 / 401 » Decisive Markov Chains |
ICML
2008
IEEE
16 years 2 months ago
2008
IEEE
Partially Observable Markov Decision Processes (POMDPs) have succeeded in planning domains that require balancing actions that increase an agent's knowledge and actions that ...
ICML
2006
IEEE
16 years 2 months ago
2006
IEEE
We introduce relational temporal difference learning as an effective approach to solving multi-agent Markov decision problems with large state spaces. Our algorithm uses temporal ...
ICML
2006
IEEE
16 years 2 months ago
2006
IEEE
When the transition probabilities and rewards of a Markov Decision Process are specified exactly, the problem can be solved without any interaction with the environment. When no s...
110
click to vote
ICML
2006
IEEE
16 years 2 months ago
2006
IEEE
For a Markov Decision Process with finite state (size S) and action spaces (size A per state), we propose a new algorithm--Delayed Q-Learning. We prove it is PAC, achieving near o...
107
click to vote
ICML
2006
IEEE
16 years 2 months ago
2006
IEEE
How should a reinforcement learning agent act if its sole purpose is to efficiently learn an optimal policy for later use? In other words, how should it explore, to be able to exp...