Tools
Sorted by:
Try your query at:
 |
 |
 |
 |
 |
 |
Results 1 - 10
of
167
Learning representation and control in Markov decision processes: New frontiers
- Foundations and Trends in Machine Learning
, 2009
"... ..."
Learning representation and control in continuous Markov decision processes
- In Proc. of the 21st National Conference on Artificial Intelligence. Menlo
, 2006
"... This paper presents a novel framework for simultaneously learning representation and control in continuous Markov decision processes. Our approach builds on the framework of proto-value functions, in which the underlying representation or basis functions are automatically derived from a spectral ana ..."
Abstract
-
Cited by 19 (6 self)
- Add to MetaCart
This paper presents a novel framework for simultaneously learning representation and control in continuous Markov decision processes. Our approach builds on the framework of proto-value functions, in which the underlying representation or basis functions are automatically derived from a spectral
Proto-value functions: A laplacian framework for learning representation and control in markov decision processes
- Journal of Machine Learning Research
, 2006
"... This paper introduces a novel spectral framework for solving Markov decision processes (MDPs) by jointly learning representations and optimal policies. The major components of the framework described in this paper include: (i) A general scheme for constructing representations or basis functions by d ..."
Abstract
-
Cited by 92 (10 self)
- Add to MetaCart
This paper introduces a novel spectral framework for solving Markov decision processes (MDPs) by jointly learning representations and optimal policies. The major components of the framework described in this paper include: (i) A general scheme for constructing representations or basis functions
Reinforcement learning for factored markov decision processes
, 2002
"... Learning to act optimally in a complex, dynamic and noisy environment is a hard prob-lem. Various threads of research from reinforcement learning, animal conditioning, oper-ations research, machine learning, statistics and optimal control are beginning to come together to offer solutions to this pro ..."
Abstract
-
Cited by 17 (0 self)
- Add to MetaCart
to this problem. I present a thesis in which novel algorithms are presented for learning the dynamics, learning the value function, and selecting good actions for Markov decision processes. The problems considered have high-dimensional factored state and action spaces, and are either fully or partially observable
Efficient Resources Allocation for Markov Decision Processes
- In Advances in Neural Information Processing Systems 13 (NIPS’01
, 2001
"... It is desirable that a complex decision-making problem in an uncertain world be adequately modeled by a Markov Decision Process (MDP) whose structural representation is adaptively designed by a parsimonious resources allocation process. Resources include time and cost of exploration, amount of memor ..."
Abstract
-
Cited by 11 (0 self)
- Add to MetaCart
It is desirable that a complex decision-making problem in an uncertain world be adequately modeled by a Markov Decision Process (MDP) whose structural representation is adaptively designed by a parsimonious resources allocation process. Resources include time and cost of exploration, amount
Efficient Solution of Markov Decision Problems with Multiscale Representations
"... Abstract — Many problems in sequential decision making and stochastic control naturally enjoy strong multiscale structure: sub-tasks are often assembled together to accomplish complex goals. However, systematically inferring and leveraging hierarchical structure has remained a longstanding challenge ..."
Abstract
- Add to MetaCart
challenge. We describe a fast multiscale procedure for repeatedly compressing or homogenizing Markov decision processes (MDPs), wherein a hierarchy of sub-problems at different scales is automatically determined. Coarsened MDPs are themselves independent, deterministic MDPs, and may be solved using any
Variable Resolution Discretization in Optimal Control
- MACHINE LEARNING
, 2001
"... The problem of state abstraction is of central importance in optimal control, reinforcement learning and Markov decision processes. This paper studies the case of variable resolution state abstraction for continuous time and space, deterministic dynamic control problems in which near-optimal policie ..."
Abstract
-
Cited by 128 (3 self)
- Add to MetaCart
The problem of state abstraction is of central importance in optimal control, reinforcement learning and Markov decision processes. This paper studies the case of variable resolution state abstraction for continuous time and space, deterministic dynamic control problems in which near
Multiscale Markov Decision Problems: Compression, Solution, and Transfer Learning
, 2012
"... Many problems in sequential decision making and stochastic control often have natu-ral multiscale structure: sub-tasks are assembled together to accomplish complex goals. Systematically inferring and leveraging hierarchical structure, particularly beyond a single level of abstraction, has remained a ..."
Abstract
- Add to MetaCart
a longstanding challenge. We describe a fast multi-scale procedure for repeatedly compressing, or homogenizing, Markov decision processes (MDPs), wherein a hierarchy of sub-problems at different scales is automatically deter-mined. Coarsened MDPs are themselves independent, deterministic MDPs
Reinforcement learning based algorithms for average cost Markov decision processes
, 2007
"... This article proposes several two-timescale simulation-based actor-critic algorithms for solution of infinite horizon Markov Decision Processes with finite state-space under the average cost criterion. Two of the algorithms are for the compact (non-discrete) action setting while the rest are for fin ..."
Abstract
-
Cited by 5 (4 self)
- Add to MetaCart
This article proposes several two-timescale simulation-based actor-critic algorithms for solution of infinite horizon Markov Decision Processes with finite state-space under the average cost criterion. Two of the algorithms are for the compact (non-discrete) action setting while the rest
Results 1 - 10
of
167
