Multiagent approaches are well suited to designing autonomous solutions for systems that feature complex interactions between many individuals such as in autonomous traffic systems and multi-robot exploration systems. However, creating autonomous agents that function effectively in these systems is a challenging task. In these complex environments, agents need informative reward...
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...
Autonomous agents that sense, decide, act, and coordinate effectively with each other are critical in many real-world domains such as autonomous driving, search and rescue missions, air traffic management, and underwater or deep space exploration. All such domains share a key difficulty: though high-level mission goals are clear to system...
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...
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...
The overall focus of this thesis is on the distribution of specific lipids and membrane proteins of the external and internal membranes of plant cells, in the context of the roles that those lipids and proteins may play in microbe-plant interactions. The work includes the development of several new tools,...
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...
Markov Decision Processes (MDPs) are the de-facto formalism for studying sequential decision making problems with uncertainty, ranging from classical problems such as inventory control and path planning, to more complex problems such as reservoir control under rainfall uncertainty and emergency response optimization for fire and medical emergencies. Most prior research...
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...
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)...