Difference between revisions of "Learning"

From BP Wiki
Jump to: navigation, search
(Contens of reference material)
(Reference Materials)
 
(7 intermediate revisions by one user not shown)
Line 1: Line 1:
= Adaptive Behavioral Programming =  
+
= Adaptive Behavioral Programming =
  
== Reference Materials ==
+
We introduce a way to program adaptive reactive
* Paper: [http://www.wisdom.weizmann.ac.il/~harel/papers/Adaptive%20BP.pdf Adaptive Behavioral Programming]
+
systems, using behavioral programming.
* See [http://www.wisdom.weizmann.ac.il/~bprogram/code/ReinforcementLearningBPJ.zip reference materials ]
+
Extending the semantics of BPJ with reinforcements
 +
allows the programmer not only to specify what
 +
the system should do or must not do, but also what it should
 +
try to do, in an intuitive and incremental way. By integrating
 +
behavioral programs with reinforcement learning methods,
 +
the program can adapt to the environment, and try to achieve
 +
the desired goals.
  
== Contents of reference material ==
+
== Reference Materials ==
* A base version of BPJ  
+
* Paper: [http://www.wisdom.weizmann.ac.il/~harel/papers/Adaptive%20BP.pdf Adaptive Behavioral Programming]
* A Java library with extensions to BPJ for reinforcement learning. Import and add to the classpath
+
* [http://www.wisdom.weizmann.ac.il/~bprogram/code/ReinforcementLearningBPJ.zip Code and examples]: <br/>
* Example: A Salad cutting robot. The b-threads provide an underspecification for a simulated robot that needs to pick up vegetables, cut them and serve them to customers. Using reinforcement learning, the robot learns the correct o in which to execute these actions.
+
** A base version of BPJ.
* Example: Tic Tac Toe, where the application learns how to play despite underspecification.
+
** A Java library with extensions to BPJ for reinforcement learning. Import and add to the classpath.
 +
** Example: A Salad cutting robot. The b-threads provide an incomplete specification for a simulated robot that needs to pick up vegetables, cut them and serve them to customers. Using reinforcement learning, the robot learns the correct order in which to execute these actions.
 +
** Example: Tic Tac Toe, where the application learns how to play despite underspecification.

Latest revision as of 10:03, 28 April 2014

Adaptive Behavioral Programming

We introduce a way to program adaptive reactive systems, using behavioral programming. Extending the semantics of BPJ with reinforcements allows the programmer not only to specify what the system should do or must not do, but also what it should try to do, in an intuitive and incremental way. By integrating behavioral programs with reinforcement learning methods, the program can adapt to the environment, and try to achieve the desired goals.

Reference Materials

  • Paper: Adaptive Behavioral Programming
  • Code and examples:
    • A base version of BPJ.
    • A Java library with extensions to BPJ for reinforcement learning. Import and add to the classpath.
    • Example: A Salad cutting robot. The b-threads provide an incomplete specification for a simulated robot that needs to pick up vegetables, cut them and serve them to customers. Using reinforcement learning, the robot learns the correct order in which to execute these actions.
    • Example: Tic Tac Toe, where the application learns how to play despite underspecification.