13 search results - page 1 / 3 » Model-free reinforcement learning as mixture learning |
NIPS
2001
13 years 6 months ago
2001
We propose a new approach to reinforcement learning which combines least squares function approximation with policy iteration. Our method is model-free and completely off policy. ...
ICML
2009
IEEE
14 years 5 months ago
2009
IEEE
We cast model-free reinforcement learning as the problem of maximizing the likelihood of a probabilistic mixture model via sampling, addressing both the infinite and finite horizo...
ICML
2007
IEEE
14 years 5 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...
JMLR
2010
12 years 11 months ago
2010
With the goal to generate more scalable algorithms with higher efficiency and fewer open parameters, reinforcement learning (RL) has recently moved towards combining classical tec...
NIPS
1998
13 years 6 months ago
1998
In this paper, we consider Markov Decision Processes (MDPs) with error states. Error states are those states entering which is undesirable or dangerous. We define the risk with re...