448 search results - page 42 / 90 » Abstraction in Predictive State Representations |
158
click to vote
AMAST
2008
Springer
15 years 8 months ago
2008
Springer
Abstract. We present a static analysis technique for modeling and approximating the long-run resource usage of programs. The approach is based on a quantitative semantic framework ...
161
click to vote
AAAI
2004
15 years 7 months ago
2004
CAT's knowledge base contains abstract task or example "abstract flight reservation task," which can be included in a workflow as placeholders. CAT will gest that us...
133
click to vote
JMLR
2010
15 years 29 days ago
2010
Hsu et al. (2009) recently proposed an efficient, accurate spectral learning algorithm for Hidden Markov Models (HMMs). In this paper we relax their assumptions and prove a tighte...
167
click to vote
ATAL
2007
Springer
15 years 10 months ago
2007
Springer
This paper extends the framework of dynamic influence diagrams (DIDs) to the multi-agent setting. DIDs are computational representations of the Partially Observable Markov Decisio...
262
click to vote
ILP
2007
Springer
16 years 10 days ago
2007
Springer
Abstract. Many reinforcement learning domains are highly relational. While traditional temporal-difference methods can be applied to these domains, they are limited in their capaci...