48 search results - page 4 / 10 » Metrics for Finite Markov Decision Processes |
IJFCS
2008
14 years 9 months ago
2008
We consider the equivalence problem for labeled Markov chains (LMCs), where each state is labeled with an observation. Two LMCs are equivalent if every finite sequence of observat...
MOR
2008
14 years 9 months ago
2008
We consider the average cost problem for partially observable Markov decision processes (POMDP) with finite state, observation, and control spaces. We prove that there exists an -...
NIPS
2008
14 years 11 months ago
2008
Our setting is a Partially Observable Markov Decision Process with continuous state, observation and action spaces. Decisions are based on a Particle Filter for estimating the bel...
ICML
2003
IEEE
15 years 10 months ago
2003
IEEE
We present metric?? , a provably near-optimal algorithm for reinforcement learning in Markov decision processes in which there is a natural metric on the state space that allows t...
109
click to vote
JMLR
2010
14 years 4 months ago
2010
In this paper, we propose a novel adaptive step-size approach for policy gradient reinforcement learning. A new metric is defined for policy gradients that measures the effect of ...