Tools
Sorted by:
Try your query at:
 |
 |
 |
 |
 |
 |
Results 1 - 10
of
278
Reinforcement learning with hierarchies of machines
- Advances in Neural Information Processing Systems 10
, 1998
"... We present a new approach to reinforcement learning in which the policies considered by the learning process are constrained by hierarchies of partially specified machines. This allows for the use of prior knowledge to reduce the search space and provides a framework in which knowledge can be transf ..."
Abstract
-
Cited by 285 (11 self)
- Add to MetaCart
be transferred across problems and in which component solutions can be recombined to solve larger and more complicated problems. Our approach can be seen as providing a link between reinforcement learning and “behavior-based ” or “teleo-reactive ” approaches to control. We present provably convergent algorithms
Beyond the session timeout: automatic hierarchical segmentation of search topics in query logs
- In Conference on Information and Knowledge Management (CIKM
, 2008
"... Most analysis of web search relevance and performance takes a single query as the unit of search engine interaction. When studies attempt to group queries together by task or session, a timeout is typically used to identify the boundary. However, users query search engines in order to accomplish tas ..."
Abstract
-
Cited by 147 (1 self)
- Add to MetaCart
tasks at a variety of granularities, issuing multiple queries as they attempt to accomplish tasks. In this work we study real sessions manually labeled into hierarchical tasks, and show that timeouts, whatever their length, are of limited utility in identifying task boundaries, achieving a maximum
Hierarchical Active Transfer Learning
"... We describe a unified active transfer learning framework called Hierarchical Active Transfer Learning (HATL). HATL exploits cluster structure shared between differ-ent data domains to perform transfer learning by im-puting labels for unlabeled target data and to generate effective label queries duri ..."
Abstract
- Add to MetaCart
We describe a unified active transfer learning framework called Hierarchical Active Transfer Learning (HATL). HATL exploits cluster structure shared between differ-ent data domains to perform transfer learning by im-puting labels for unlabeled target data and to generate effective label queries
Transfer in variable-reward hierarchical reinforcement learning
- In: Proc. of the Inductive Transfer workshop at NIPS
, 2005
"... We consider the problem of transferring learned knowledge among Markov Decision Processes that share the same transition dynamics but different reward functions. In particular, we assume that reward functions are described as linear combinations of reward features, and that only the feature weights ..."
Abstract
-
Cited by 33 (3 self)
- Add to MetaCart
vary among MDPs. We introduce Variable-Reward Hierarchical Reinforcement Learning (VRHRL), which leverages a cache of learned policies to speed up learning in this setting. With suitable design of the task hierarchy, VRHRL can achieve better transfer than its non-hierarchical counterpart. 1
Variability of worked examples and transfer of geometrical problem-solving skills: A cognitive-load approach
- Journal of Educational Psychology
, 1994
"... Four computer-based training strategies for geometrical problem solving in the domain of computer numerically controlled machinery programming were studied with regard to their effects on training performance, transfer performance, and cognitive load. A low- and a high-variability conventional condi ..."
Abstract
-
Cited by 149 (30 self)
- Add to MetaCart
, problem solutions can often be characterized by a hierarchical goal structure. The goal of these solutions can be attained only by successfully attaining all subgoals. Learning and performance of complex cogni-tive tasks are typically constrained by limited processing ca-
Learning hierarchical task networks by observation
- Proceedings of the Twenty-Third International Conference on Machine Learning
, 2006
"... Knowledge-based planning methods offer benefits over classical techniques, but they are time consuming and costly to construct. There has been research on learning plan knowledge from search, but this can take substantial computer time and may even fail to find solutions on complex tasks. Here we de ..."
Abstract
-
Cited by 48 (14 self)
- Add to MetaCart
describe another approach that observes sequences of operators taken from expert solutions to problems and learns hierarchical task networks from them. The method has similarities to previous algorithms for explanation-based learning, but differs in its ability to acquire hierarchical structures
Hierarchical Transfer of Semantic Attributes
"... In the prevailing approach, attributes are learned from all seen classes and then reused to describe or classify an unseen one. However, this doesn’t account for the high intra-attribute variance. Using all the seen classes helps in ..."
Abstract
- Add to MetaCart
In the prevailing approach, attributes are learned from all seen classes and then reused to describe or classify an unseen one. However, this doesn’t account for the high intra-attribute variance. Using all the seen classes helps in
A Hierarchical Characterization of a Live Streaming Media Workload
- IEEE/ACM Transactions on Networking
, 2002
"... We present what we believe to be the first thorough characterization of live streaming media content delivered over the Internet. Our characterization of over five million requests spanning a 28-day period is done at three increasingly granular levels, corresponding to clients, sessions, and transfe ..."
Abstract
-
Cited by 94 (13 self)
- Add to MetaCart
We present what we believe to be the first thorough characterization of live streaming media content delivered over the Internet. Our characterization of over five million requests spanning a 28-day period is done at three increasingly granular levels, corresponding to clients, sessions
Modeling Human Transfer Learning with the Hierarchical Dirichlet Process
"... Transfer learning can be described as the distillation of abstract knowledge from one learning domain or task and the reuse of that knowledge in a related domain or task. In categorization settings, transfer learning is the modification by past learning experience of prior expectations about what ca ..."
Abstract
-
Cited by 6 (0 self)
- Add to MetaCart
Transfer learning can be described as the distillation of abstract knowledge from one learning domain or task and the reuse of that knowledge in a related domain or task. In categorization settings, transfer learning is the modification by past learning experience of prior expectations about what
State Abstraction for Programmable Reinforcement Learning Agents
- In Proceedings of the Eighteenth National Conference on Artificial Intelligence
, 2002
"... Safe state abstraction in reinforcement learning allows an agent to ignore aspects of its current state that are irrelevant to its current decision, and therefore speeds up dynamic programming and learning. This paper explores safe state abstraction in hierarchical reinforcement learning, where ..."
Abstract
-
Cited by 101 (3 self)
- Add to MetaCart
Safe state abstraction in reinforcement learning allows an agent to ignore aspects of its current state that are irrelevant to its current decision, and therefore speeds up dynamic programming and learning. This paper explores safe state abstraction in hierarchical reinforcement learning, where
Results 1 - 10
of
278
