945 search results - page 79 / 189 » Dialog Convergence and Learning |
121
Voted
ICML
2000
IEEE
16 years 4 months ago
2000
IEEE
This paper discusses theoretical and experimental aspects of gradient-based approaches to the direct optimization of policy performance in controlled ??? ?s. We introduce ??? ?, a...
115
Voted
WSC
2008
15 years 5 months ago
2008
Reinforcement Learning (RL) is a simulation-based technique useful in solving Markov decision processes if their transition probabilities are not easily obtainable or if the probl...
118
Voted
ECAI
2008
Springer
15 years 5 months ago
2008
Springer
In this paper, we propose a policy gradient reinforcement learning algorithm to address transition-independent Dec-POMDPs. This approach aims at implicitly exploiting the locality...
109
Voted
EMNLP
2008
15 years 5 months ago
2008
We propose a new graph-based semisupervised learning (SSL) algorithm and demonstrate its application to document categorization. Each document is represented by a vertex within a ...
121
Voted
IJCAI
1989
15 years 4 months ago
1989
This paper describes an explanation-based approach lo learning plans despite a computationally intractable domain theory. In this approach, the system learns an initial plan using...