252 search results - page 12 / 51 » Learning Partially Observable Action Models: Efficient Algor... |
90
Voted
ECML
2007
Springer
15 years 5 months ago
2007
Springer
We present Policy Gradient Actor-Critic (PGAC), a new model-free Reinforcement Learning (RL) method for creating limited-memory stochastic policies for Partially Observable Markov ...
ICML
2008
IEEE
16 years 14 days ago
2008
IEEE
Exponential Family PSR (EFPSR) models capture stochastic dynamical systems by representing state as the parameters of an exponential family distribution over a shortterm window of...
COLT
2008
Springer
15 years 1 months ago
2008
Springer
Inspired by longstanding lines of research in sociology and related fields, and by more recent largepopulation human subject experiments on the Internet and the Web, we initiate a...
ECML
2007
Springer
15 years 5 months ago
2007
Springer
In this article, we present an idea for solving deterministic partially observable markov decision processes (POMDPs) based on a history space containing sequences of past observat...
102
Voted
COLT
2005
Springer
15 years 1 months ago
2005
Springer
External regret compares the performance of an online algorithm, selecting among N actions, to the performance of the best of those actions in hindsight. Internal regret compares ...