Matching Items (2)
Filtering by
- All Subjects: Fault scarps
- All Subjects: ROS
- All Subjects: Volcanic Tableland
- Creators: Das, Jnaneshwar
- Creators: Scott, Tyler
Description
This work has improved the quality of the solution to the sparse rewards problemby combining reinforcement learning (RL) with knowledge-rich planning. Classical
methods for coping with sparse rewards during reinforcement learning modify the
reward landscape so as to better guide the learner. In contrast, this work combines
RL with a planner in order to utilize other information about the environment. As
the scope for representing environmental information is limited in RL, this work has
conflated a model-free learning algorithm – temporal difference (TD) learning – with
a Hierarchical Task Network (HTN) planner to accommodate rich environmental
information in the algorithm. In the perpetual sparse rewards problem, rewards
reemerge after being collected within a fixed interval of time, culminating in a lack of a
well-defined goal state as an exit condition to the problem. Incorporating planning in
the learning algorithm not only improves the quality of the solution, but the algorithm
also avoids the ambiguity of incorporating a goal of maximizing profit while using
only a planning algorithm to solve this problem. Upon occasionally using the HTN
planner, this algorithm provides the necessary tweak toward the optimal solution. In
this work, I have demonstrated an on-policy algorithm that has improved the quality
of the solution over vanilla reinforcement learning. The objective of this work has
been to observe the capacity of the synthesized algorithm in finding optimal policies to
maximize rewards, awareness of the environment, and the awareness of the presence
of other agents in the vicinity.
ContributorsNandan, Swastik (Author) / Pavlic, Theodore (Thesis advisor) / Das, Jnaneshwar (Thesis advisor) / Berman, Spring (Committee member) / Arizona State University (Publisher)
Created2022
Description
Rock traits (grain size, shape, orientation) are fundamental indicators of geologic processes including geomorphology and active tectonics. Fault zone evolution, fault slip rates, and earthquake timing are informed by examinations of discontinuities in the displacements of the Earth surface at fault scarps. Fault scarps indicate the structure of fault zones fans, relay ramps, and double faults, as well as the surface process response to the deformation and can thus indicate the activity of the fault zone and its potential hazard. “Rocky” fault scarps are unusual because they share characteristics of bedrock and alluvial fault scarps. The Volcanic Tablelands in Bishop, CA offer a natural laboratory with an array of rocky fault scarps. Machine learning mask-Region Convolutional Neural Network segments an orthophoto to identify individual particles along a specific rocky fault scarp. The resulting rock traits for thousands of particles along the scarp are used to develop conceptual models for rocky scarp geomorphology and evolution. In addition to rocky scarp classification, these tools may be useful in many sedimentary and volcanological applications for particle mapping and characterization.
ContributorsScott, Tyler (Author) / Arrowsmith, Ramon (Thesis advisor) / Das, Jnaneshwar (Committee member) / DeVecchio, Duane (Committee member) / Arizona State University (Publisher)
Created2020