Differences

This shows you the differences between two versions of the page.

--- public:t-622-arti-07-1:thought_questions [2007/01/18 16:46] – vignir
+++ public:t-622-arti-07-1:thought_questions [2024/04/29 13:33] (current) – external edit 127.0.0.1
@@ Line 8: / Line 8: @@
 Examples of bad thought questions:
-Q: What is an agent
+Q: What is an agent?\\
 A: An agent is anything that can be viewed as perceiving its environment through sensors and acting upon that environment through actuators.
-Q: What types of agents are there:
+Q: What types of agents are there:\\
 A: Simple reflex, model-based, goal-based and utility-based
 Examples of good thought questions:
-Q: Should the critic element of a learning agent be static or dynamic, meaning that it could change over time?
+Q: Should the critic element of a learning agent be static or dynamic, meaning that it could change over time?\\
+A: It should be static so that all the experience that has been gathered doesn't become invalid.\\
+A: It should be dynamic because if the environment is dynamic, the critic should be able to adjust to it\\
+A: It should only change if its goals change.
-A: It should be static so that all the experience that has been gathered doesn't become invalid.
-A: It should be dynamic because if the environment is dynamic, the critic should be able to adjust to it
+Q: How can learning improve the types of agents mentioned in the chapter.\\
+A: Simple reflex agents could learn new if-then rules or change its own. Model-based agents could use learning to update their models.  Goal-based agents could use learning to improve the plan search. Utility-based agents can use learning to improve its utility function
-A: It should only change if its goals change.
+Q: Is it good for the programmer to know the environment which his/her agent will operate within?\\
+A: Yes, because it will create a better agent.\\
+A: No, because there is a danger of the agent's design being too dependent on the environment and its attributes.\\
+----
+Remember:
+    * Give answers to your questions. I received some very good questions but no answers to them. I can´t give a full mark for questions without answers.
+    * Give more than one answer. This is a good way to show "the quality of your thought" as you need to look at the problem from more than one side.
+    * The questions don´t need to have complete answers. If you can´t really answer your question you might be on the right track :)
+    * Try imagining that your sitting in a café with some of your peers from the class. How would you pose an interesting question from the text you just read
+    * The questions don´t need be straight from the text. Maybe you could form the question around what you could do with the technology discussed in the text
-Q: How can learning improve the types of agents mentioned in the chapter.
-A: Simple reflex agents could learn new if-then rules or change its own. Model-based agents could use learning to update their models.  Goal-based agents could use learning to improve the plan search. Utility-based agents can use learning to improve its utility function
-Q: Is it good for the programmer to know the environment which his/her agent will operate within?
-A: Yes, because it will create a better agent.
-A: No, because there is a danger of the agent's design being too dependent on the environment and its attributes.