RLAI
 
  Reinforcement Learning Competition


NIPS Workshop: The First Annual
Reinforcement Learning Competition




The ambition of this page is to provide answers to questions about the RL-Glue , RL-Library and 2006 NIPS Competition. To add a new question click "Extend this Page" at the bottom of the page.

Back to main workshop page

 
       How ...

       What ...
          ... does Observation mean?
          ... task specification are we supposed to use?

       Why ...

       Problems:

 


Question: What does Observation mean? Why does the RL-Glue not pass around "states"?

Answer: Observation is a more  general term, to which the concept of state, and state of say mountain car is a subset. Observation can be an array of doubles or an int or whatever. This is controlled in the common types file for each agent-environment pair.



Question: Where is the "environmental state" stored in RL-Glue? In other systems, such as CLSquare, the old state is passed to the environment step function.

Answer: The environment in RL-Glue is responsible for keeping  track of the current "state" and computing the next "state" given an action. Old state need not be passed. The state stays within the  environement. The next_state method in CLSquare is basically the same as env_step in RL-Glue.