How can an agent generalize its knowledge to new circumstances? To learn
effectively an agent acting in a sequential decision problem must make intelligent action selection choices based on its available knowledge. This dissertation focuses on Bayesian methods of representing learned knowledge and develops novel algorithms that exploit the represented...
The conservation community has long recognized the critical role that agricultural landowners play in efforts to improve fish and wildlife habitat in order to recover threatened and endangered species. In many rural areas dominated by agricultural working landscapes, government agencies like the U.S. Fish and Wildlife Service (USFWS) struggle to...
This dissertation incorporates coalition formation and probabilistic planning towards a domain-independent automated planning solution scalable to multiple heterogeneous robots in complex domains. The first research direction investigates the effectiveness of Task Fusion and introduces heuristics that improve task allocation and result in better quality plans, while requiring lower computational cost...
Autonomous multiagent teams can be used in complex exploration tasks to both expedite the exploration and improve the efficiency. However, use of multiagent systems presents additional challenges. Specifically, in domains where the agents' actions are tightly coupled, coordinating multiple agents to achieve cooperative behavior at the group level is difficult....
In 2017, the cost of congestion in the United States was around 305 billion dollars, and city-dwellers, on average, lost 1400 dollars while sitting 42 hours in traffic jams. Aiming for better mobility and more efficient utilization of the transportation network, emerging connected and autonomous vehicle (CAV) technologies and their...
This work is inspired by problems in natural resource management centered on the challenge of invasive species. Computing optimal management policies for maintaining ecosystem sustainable is challenging. Many ecosystem management problems can be formulated as MDP (Markov Decision Process) planning problems. In a simulator-defined MDP, the Markovian dynamics and rewards...
Writing a program that performs well in a complex environment is a challenging task. In such problems, a method of deterministic programming combined with reinforcement learning (RL) can be helpful. However, current systems either force developers to encode knowledge in very specific forms (e.g., state-action features), or assume advanced RL...
We do not know how to align a very intelligent AI agent's behavior with human interests. I investigate whether—absent a full solution to this AI alignment problem—we can build smart {\ai} agents which have limited impact on the world, and which do not autonomously seek power. In this thesis, I...
This thesis considers the problem in which a teacher is interested in teaching action policies to computer agents for sequential decision making. The vast majority of policy
learning algorithms o er teachers little flexibility in how policies are taught. In particular,
one of two learning modes is typically considered: 1)...
Potentially relevant literature for the years 1990-1999 was identified by (a) conducting keyword searches of computerized bibliographic databases, especially CAB Abstracts and Aquatic Sciences and Fisheries Abstracts, (b) reading through the tables of contents of a few especially relevant journals, (c) searching the internet for pertinent bibliographies, and (d) to...