5757 search results - page 265 / 1152 » Dynamic Policy Programming |
166
click to vote
FASE
2010
Springer
16 years 1 months ago
2010
Springer
Actor programs consist of a number of concurrent objects called actors, which communicate by exchanging messages. Nondeterminism in actors results from the different possible orde...
207
click to vote
PLDI
2012
ACM
13 years 9 months ago
2012
ACM
Existing dynamic race detectors suffer from at least one of the following three limitations: (i) space overhead per memory location grows linearly with the number of parallel thre...
154
click to vote
PADL
2010
Springer
16 years 3 months ago
2010
Springer
Abstract. A Prolog implementation of an In-lined Reference Monitoring system prototype for Adobe ActionScript Bytecode programs is presented. Prolog provides an elegant framework f...
152
click to vote
NIPS
2000
15 years 8 months ago
2000
We present an expressive agent design language for reinforcement learning that allows the user to constrain the policies considered by the learning process.The language includes s...