On the Hardness of Finding Symmetries in Markov Decision Processes
author:
Balaraman Ravindran,
Department of Computer Science and Engineering, Indian Institute of Technology
Description
In this work we address the question of finding symmetries of a given MDP. We show that the problem is Isomorphism Complete, that is, the problem is polynomially equivalent to verifying whether two graphs are isomorphic. Apart from the theoretical importance of this result it has an important practical application. The reduction presented can be used together with any off-the-shelf Graph Isomorphism solver, which performs well in the average case, to find symmetries of an MDP. In fact, we present results of using NAutY (the best Graph Isomorphism solver currently available), to find symmetries of MDPs.
You might be experiencing some problems with Your Video player.
| Slides | |
| 0:00 | On the Hardness of Finding Symmetries in Markov Decision Processes |
| 0:27 | Outline |
| 0:39 | Overview |
| 2:01 | Outline - Introduction |
| 2:01 | Stochastic Sequential Decision Making |
| 2:28 | Solution of an MDP |
| 2:33 | Outline - Introduction |
| 2:34 | Reduced Model - Formal definition |
| 3:40 | Reduced Model - Significance |
| 4:24 | Symmetry informally |
| 4:59 | Symmetry Formal Definition |
| 6:02 | Problem |
| 6:26 | Outline - Symmetries in MDPs |
| 6:29 | Problem Simplification |
| 6:44 | Isomorphism Completeness |
| 7:07 | List of relevant Isomorphism Complete Problems |
| 7:45 | Outline |
| 8:34 | Set Bijections |
| 9:52 | Set Bijections example |
| 11:01 | An example (1) |
| 11:14 | An example (2) |
| 11:55 | An example (3) |
| 13:43 | An example (4) |
| 13:47 | An example (3) |
| 14:01 | An example (4) |
| 14:45 | An example (5) |
| 16:15 | Construction provides the Generators of AutM |
| 16:36 | Significance |
| 16:46 | Nauty - No Automorphisms, Yes? |
| 17:15 | Nauty Integration |
| 17:24 | Outline - Symmetries in MDPs |
| 17:25 | G -Reduced Image Algorithm IJCAI 07 |
| 17:49 | Outline - Symmetries in MDPs |
| 17:51 | G -Reduced Image Algorithm IJCAI 07 |
| 17:52 | Experimental Setup - Probabilistic GridWorld |
| 17:54 | Experimental Setup - GridWorld Soccer |
| 18:28 | Results - Probabilistic GridWorld |
| 18:59 | Results - GridWorld Soccer |
| 19:45 | Summary |
| 20:24 | Thank You! |
Lecture rating
| People found this lecture: | ||
| Worth seeing | ||
| because it is: | ||
| Valuable and informative | ||
| Well presented | ||
| Easily understandable | ||
| Acceptably recorded | ||
| You need to login to cast your vote. | ||
Report a problem or upload files
If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Related content
Visitors who watched this lecture also watched...
SEE ALSO:
Link this page
Would you like to put a link to this lecture on your homepage?Go ahead! Copy the HTML snippet !




