Coarticulation: An approach for generating concurrent plans in markov decision processes (2005)
| Venue: | In Proceedings of the 22nd International Conference on Machine Learning (ICML-2005 |
| Citations: | 4 - 1 self |
BibTeX
@INPROCEEDINGS{Rohanimanesh05coarticulation:an,
author = {Khashayar Rohanimanesh and Sridhar Mahadevan},
title = {Coarticulation: An approach for generating concurrent plans in markov decision processes},
booktitle = {In Proceedings of the 22nd International Conference on Machine Learning (ICML-2005},
year = {2005}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
We study an approach for performing concurrent activities in Markov decision processes (MDPs) based on the coarticulation framework. We assume that the agent has multiple degrees of freedom (DOF) in the action space which enables it to perform activities simultaneously. We demonstrate that one natural way for generating concurrency in the system is by coarticulating among the set of learned activities available to the agent. In general due to the multiple DOF in the system, often there exists a redundant set of admissible sub-optimal policies associated with each learned activity. Such flexibility enables the agent to concurrently commit to several subgoals according to their priority levels, given a new task defined in terms of a set of prioritized subgoals. We present efficient approximate algorithms for computing such policies and for generating concurrent plans. We also evaluate our approach in a simulated domain. 1.
Citations
| 649 | Reinforcement learning - Sutton, Barto - 1998 |
| 238 | Bucket elimination: A unifying framework for probabilistic inference - Dechter - 1998 |
| 60 | Coordinated reinforcement learning - Guestrin, Lagoudakis, et al. - 2002 |
| 55 | How to dynamically merge markov decision processes - Singh, Cohn - 1998 |
| 46 | An efficient algorithm for finding the m most probable configurations - Nilsson |
| 35 | Algorithms for reinforcement learning - Szepesvári - 2010 |
| 32 | Prioritized goal decomposition of Markov decision processes: Toward a synthesis of classical and decision theoretic planning - Boutilier, Brafman, et al. - 1997 |
| 29 | A hybrid architecture for adaptive robot control. Doctoral dissertation - Huber - 2000 |
| 20 | Distributed planning in hierarchical factored MDPs - Guestrin, Gordon |
| 9 | Temporal abstraction in reinforcement learning. Doctoral dissertation - Precup - 2000 |
| 4 | 2004a). Coarticulation in markov decision processes - Rohanimanesh, Platt, et al. |
