2012
DOI: 10.1109/tamd.2011.2170213
|View full text |Cite
|
Sign up to set email alerts
|

Interactive Learning in Continuous Multimodal Space: A Bayesian Approach to Action-Based Soft Partitioning and Learning

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
16
0

Year Published

2012
2012
2021
2021

Publication Types

Select...
4
2
1

Relationship

2
5

Authors

Journals

citations
Cited by 10 publications
(16 citation statements)
references
References 25 publications
0
16
0
Order By: Relevance
“…This problem is known as the curse of dimensionality. One way to tackle this problem is to use the experiences in the subspaces of ”, such as O i , for decision making [11] , [12] . However, the environment in the eyes of O i is partially observable, which creates a many-to-one mapping between real states of the environment and observations in O i .…”
Section: Methodsmentioning
confidence: 99%
“…This problem is known as the curse of dimensionality. One way to tackle this problem is to use the experiences in the subspaces of ”, such as O i , for decision making [11] , [12] . However, the environment in the eyes of O i is partially observable, which creates a many-to-one mapping between real states of the environment and observations in O i .…”
Section: Methodsmentioning
confidence: 99%
“…Using different measures of expertness for agents with different experiences, the experiment results show that certain expertness measures are less sensitive when the knowledge is incorrect and data is uncertain. The uncertainty over the states can also be addressed using an automatic action-based soft partitioning of the state space [5]. This approach uses multiple agents to suggest actions based on partial observations of the state space.…”
Section: Related Workmentioning
confidence: 99%
“…RL problems with state uncertainties are addressed by [4], [5], [6], [3]. [2] addresses uncertainties over credit assignment.…”
Section: Introductionmentioning
confidence: 99%
“…In the seventh category, our group exploited possible generalization in the subspaces to have faster learning (see [13], [14]). Here a subspace refers to a sub-dimension of the original state representation, which is called the full-space.…”
Section: Introductionmentioning
confidence: 99%
“…• We explain the idea of using subspaces in RL framework for expediting the learning process in a concrete model. In the previous works by other members of our group, the idea of using subspaces for expediting the learning process has been exploited [13], [14]. However, the idea was not exploited in a mathematically rigorous manner.…”
Section: Introductionmentioning
confidence: 99%