Teachable agents: Difference between revisions
Jump to navigation
Jump to search
mNo edit summary |
No edit summary |
||
| (7 intermediate revisions by one other user not shown) | |||
| Line 1: | Line 1: | ||
{{stub}} | |||
==Definition== | ==Definition== | ||
{{ | [[Intelligent agent]]s within computer-based environments are {{quotation | autonomous entities that can exist in complex, dynamic, and open environments}} (Maes, 1997). Agents can possess distinct behaviours and goals that can be defined and adapted by the system {{quotation |as it learns appropriate “behavior” from the user and from other agents}} (Maes, 1997). | ||
[[ | '''Teachable agents''' in education are [[pedagogical agent]]s and intelligent agents at once that through programming can be 'taught' to perform certain tasks within simulation-based environments to explore and solve problems. It is believed that by allowing students to program computer agents students will benefit from the effects of [[learning by teaching]], [[discovery learning]] and more generally, [[project-oriented learning]]. | ||
{{quotationbox| | |||
Programming intelligent agents requires several important processes: | Programming intelligent agents requires several important processes: | ||
# defining what the agent needs to know | |||
# defining a representation of this knowledge | |||
# and programming this knowledge into the agent. | |||
This process of evaluating the needs of the agent to perform a task can lead to deeper understanding of the domain the agent needs to know about. | |||
}} (Brophy et al. 1998). | |||
See also [[logo]], [[microworld]], [[simulation]]. | |||
==Designing effective teachable agents== | |||
Swartz & Blair describe four features of teachable agents (TA) that enable students to take advantage of the inherent [[learning by teaching]] scenario: | |||
# explicit well-structured shared visual representations of the TA's thinking and reasoning | |||
# independent performance of the agent so that the effects of the student's teaching provide feedback | |||
# the agent’s ability to model productive learner behavior so as to provide guidance to the students about what needs to be taught or clarified. | |||
# embedding the agent in environments that support teaching, including a larger context and external domain-specific resources. | |||
Brophy et al. (1998) outline the major considerations and steps in designing an effective teaching agent within a simulation environment: | |||
* evaluate how an agent acts and how it interacts with other agents (dependencies) in the simulation environment | |||
* translate a hypothesis into an agent's actions/interactions | |||
** use a visual programming environment (e.g. [[AgentSheets]]) to program sets of propositions defining the behavior of the agents | |||
** identify conditions when specific actions should be taken by agents (instigated through ''click'' and ''drag'' options) | |||
* evaluate the agent by running the simulation to see if desired outcome has been effectively modelled. | |||
{{quotationbox | | |||
Used as a learning environment, the designers are learners trying to model the dynamics of complex situations. This inquiry process of evaluation, implement and test provides an excellent learning opportunity that requires very little programming experience}} ([http://www.teachableagents.org/papers/ta_workshop.html Brophy et al., 1998]) | |||
==Examples== | |||
[http://www.teachableagents.org/betty.php BETTY] | |||
==References== | |||
* Blair, K., Schwartz, D., Biswas, G. & Leelawong, K. (2006). Pedagogical Agents for Learning by Teaching: Teachable Agents, Educational Technology & Society, Special Issue on Pedagogical Agents.[http://www.teachableagents.org/papers/Final-edtechTA.pdf PDF] | |||
* Brophy S., Schwartz, D., Biswas, G., & Bransford, J. (1998, August). Learning Through Programmable Agents. Presented at Workshop on Pedagogical Agents, ITS '98, San Antonio, TX, August 1998.[http://www.teachableagents.org/papers/ta_workshop.html HTML] | |||
[[Category:Artificial intelligence and education]] | |||
Latest revision as of 16:26, 31 July 2009
Definition
Intelligent agents within computer-based environments are “autonomous entities that can exist in complex, dynamic, and open environments” (Maes, 1997). Agents can possess distinct behaviours and goals that can be defined and adapted by the system “as it learns appropriate “behavior” from the user and from other agents” (Maes, 1997).
Teachable agents in education are pedagogical agents and intelligent agents at once that through programming can be 'taught' to perform certain tasks within simulation-based environments to explore and solve problems. It is believed that by allowing students to program computer agents students will benefit from the effects of learning by teaching, discovery learning and more generally, project-oriented learning.
Programming intelligent agents requires several important processes:
- defining what the agent needs to know
- defining a representation of this knowledge
- and programming this knowledge into the agent.
(Brophy et al. 1998).
See also logo, microworld, simulation.
Designing effective teachable agents
Swartz & Blair describe four features of teachable agents (TA) that enable students to take advantage of the inherent learning by teaching scenario:
- explicit well-structured shared visual representations of the TA's thinking and reasoning
- independent performance of the agent so that the effects of the student's teaching provide feedback
- the agent’s ability to model productive learner behavior so as to provide guidance to the students about what needs to be taught or clarified.
- embedding the agent in environments that support teaching, including a larger context and external domain-specific resources.
Brophy et al. (1998) outline the major considerations and steps in designing an effective teaching agent within a simulation environment:
- evaluate how an agent acts and how it interacts with other agents (dependencies) in the simulation environment
- translate a hypothesis into an agent's actions/interactions
- use a visual programming environment (e.g. AgentSheets) to program sets of propositions defining the behavior of the agents
- identify conditions when specific actions should be taken by agents (instigated through click and drag options)
- evaluate the agent by running the simulation to see if desired outcome has been effectively modelled.
Used as a learning environment, the designers are learners trying to model the dynamics of complex situations. This inquiry process of evaluation, implement and test provides an excellent learning opportunity that requires very little programming experience
Examples
References
- Blair, K., Schwartz, D., Biswas, G. & Leelawong, K. (2006). Pedagogical Agents for Learning by Teaching: Teachable Agents, Educational Technology & Society, Special Issue on Pedagogical Agents.PDF
- Brophy S., Schwartz, D., Biswas, G., & Bransford, J. (1998, August). Learning Through Programmable Agents. Presented at Workshop on Pedagogical Agents, ITS '98, San Antonio, TX, August 1998.HTML