Douglas Pearson: "Learning Procedural Planning Knowledge in Complex Environments". Ph.D. Thesis: University of Michigan, 1996.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....of what constitutes an error (e.g. 6] most refinement frameworks avoid the underlying complexities of the error detection problem. Instead, these frameworks make one or more limiting assumptions: that the nature of an error is very constrained, and perhaps not even context dependent [2] [9]; or that the task is limited to noninteractive problems such as classification, where errors can be detected without comparing to long episodes of human behavior [2] 6] 9] In the field of intelligent tutoring systems (ITS) the error detection problem is addressed with slightly different ....

.... or more limiting assumptions: that the nature of an error is very constrained, and perhaps not even context dependent [2] 9] or that the task is limited to noninteractive problems such as classification, where errors can be detected without comparing to long episodes of human behavior [2] 6] [9]. In the field of intelligent tutoring systems (ITS) the error detection problem is addressed with slightly different assumptions. In this community, the goal is to determine 3. Error Detection Methods When examining potential error detection methodologies, we make two main assumptions. The ....

Douglas Pearson: "Learning Procedural Planning Knowledge in Complex Environments". Ph.D. Thesis: University of Michigan, 1996.

....knowledge that could be used to plan new approaches to task performance. One major advantage of using Soar operators is the potential to use KnoMic in conjunction with other learning systems which generate Soar operators including INSTRUCTO Soar [3] which learns from expert instruction and IMPROV [5] which learns through unsupervised experimentation. 4 KnoMic The KnoMic system makes use of many of the techniques used by behavioral cloning to learn effectively in the complex flight simulator environment. The operators are expressed as separate selection and application rules, the matching of ....

Pearson, D.J. Learning Procedural Planning Knowledge in Complex Environments. PhD thesis, University of Michigan, Dept. of Electrical Engineering and Computer Science, 1996.

....relevance to our problem because it exhaustively generates theory transformations, which is not practical in continuous domains. Some planning based systems that interact with an environment also demonstrate the use of theory revision to complete their tasks successfully. If Gil s (1992) EXPO, or Pearson s (1996) IMPROV fail to achieve a goal expected from planning, they attempt to correct their plan knowledge through interaction with the environment. Both agents take a variety of actions in the world, then analyze the effects to determine how to perform better in the future. Our problem is fundamentally ....

Pearson, D. J. (1996). Learning procedural planning knowledge in complex environments. Doctoral dissertation, University of Michigan, Ann Arbor, MI.

....it just receives position traces on their own. Unsupervised learning techniques are necessary to cope with this restriction. Some planning based systems that interact with an environment also demonstrate the use of theory revision to complete their tasks successfully. If Gil s (1992) EXPO, or Pearson s (1996) IMPROV fail to achieve a goal expected from planning, they attempt to correct their plan knowledge through interaction with the environment. Both agents take a variety of actions in the world, then analyze the effects to determine how to perform better in the future. Our problem is ....

Pearson, D. J. (1996). Learning procedural planning knowledge in complex environments.

....with the robotics approach of learning action costs. Rogue learns from the execution experience of a real robot to identify the conditions under which actions have different probabilities. AI research for improving domain models has focussed on correcting action models and learning control rules [Pearson, 1996; P erez, 1995; Shen, 1994; Wang, 1996] Unfortunately, most of these systems rely on complete and correct sensing, in simulated environments with no noise or exogenous events. In robotics, the difficulties posed by real world domains have generally been limited to learning action parameters, such ....

Pearson, D. J. 1996. Learning Procedural Planning Knowledge in Complex Environments. Ph.D. Dissertation, Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI. Available as Technical Report CSE-TR-309-96.

....operational parameters for better actuator control (e.g. 2, 4, 19] Instead of improving low level actuator control, our work focusses at the planning stages of the system. A few other researchers have explored this area as well, learning costs of actions, or their applicability criteria (e.g. [11, 14, 21, 18, 24]) Reinforcement Learning techniques [11] learn the value of being in a particular state, which is then used to select the optimal action. This approach can be viewed as learning the integral of action costs. However, most Reinforcement Learning techniques are unable to generalize learned ....

....and as a result, they have only been used in small domains 1 . Moreover, Reinforcement Learning techniques typically learn a universal action model for a single goal. Our situation dependent learning approach learns knowledge that will be transferrable to other similar tasks. IMPROV [18] learns action descriptions, but its performance degrades dramatically with environmental noise. Clementine [14] and CSL [24] both learn sensor utilities, including which sensor to use for what information. LIVE [21] learns a model of the environment, as well as the costs of applying actions in ....

D. J. Pearson. Learning Procedural Planning Knowledge in Complex Environments. PhD thesis, Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, 1996. Available as Technical Report CSE-TR-309-96.

No context found.

D. J. Pearson. Learning Procedural Planning Knowledge in Complex Environments. PhD thesis, Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, 1996.

No context found.

Pearson, D. J. Learning Procedural Planning Knowledge in Complex Environments. PhD thesis, Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, 1996.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC