Log in

Information on

Adding a talk details

If you have a question about this talk, please contact Shakir Mohamed .

Recent work has shown that finding a near-optimal policy in an MDP or POMDP can be framed as an inference problem. We will focus on:

“Probabilistic inference for solving (PO)MDPs,” Toussaint et. al. (2006)

and perhaps talk a little bit about:

“Hierarchical POMDP Controller Optimization by Likelihood Maximization,” Toussaint et. al. (2008)

and discuss implications for planning and reinforcement learning.

Note that ex-directory lists are not shown.

Recent work has shown that finding a near-optimal policy in an MDP or POMDP can be framed as an inference problem. We will focus on:

“Probabilistic inference for solving (PO)MDPs,” Toussaint et. al. (2006)

and perhaps talk a little bit about:

“Hierarchical POMDP Controller Optimization by Likelihood Maximization,” Toussaint et. al. (2008)

and discuss implications for planning and reinforcement learning.